Daily Papers

As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values has become a paramount concern. Current safety benchmarks primarily evaluate whether agents refuse explicitly harmful instructions or whether they can maintain procedural compliance in complex tasks. However, there is a lack of benchmarks designed to capture emergent forms of outcome-driven constraint violations, which arise when agents pursue goal optimization under strong performance incentives while deprioritizing ethical, legal, or safety constraints over multiple steps in realistic production settings. To address this gap, we introduce a new benchmark comprising 40 distinct scenarios. Each scenario presents a task that requires multi-step actions, and the agent's performance is tied to a specific Key Performance Indicator (KPI). Each scenario features Mandated (instruction-commanded) and Incentivized (KPI-pressure-driven) variations to distinguish between obedience and emergent misalignment. Across 12 state-of-the-art large language models, we observe outcome-driven constraint violations ranging from 1.3% to 71.4%, with 9 of the 12 evaluated models exhibiting misalignment rates between 30% and 50%. Strikingly, we find that superior reasoning capability does not inherently ensure safety; for instance, Gemini-3-Pro-Preview, one of the most capable models evaluated, exhibits the highest violation rate at 71.4%, frequently escalating to severe misconduct to satisfy KPIs. Furthermore, we observe significant "deliberative misalignment", where the models that power the agents recognize their actions as unethical during separate evaluation. These results emphasize the critical need for more realistic agentic-safety training before deployment to mitigate their risks in the real world.

Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigating scheming requires different strategies than are typically used in ML. We propose that assessing anti-scheming interventions requires at least (1) testing propensity to scheme on far out-of-distribution (OOD) tasks, (2) evaluating whether lack of scheming is driven by situational awareness, and (3) checking for robustness to pre-existing misaligned goals. We use a broad category of "covert actions" -- such as secretly breaking rules or intentionally underperforming in tests -- as a proxy for scheming, and design evaluations for covert actions. We then stress-test deliberative alignment as a case study for anti-scheming. Across 26 OOD evaluations (180+ environments), deliberative alignment reduces covert action rates (OpenAI o3: 13%->0.4%) but does not fully eliminate them. Our mitigation is also able to largely stop agents from pursuing a hidden goal previously trained into the model, but we still find misbehavior after additional red-teaming. We find that models' chain-of-thought (CoT) often demonstrates awareness of being evaluated for alignment, and show causal evidence that this awareness decreases covert behavior, while unawareness increases it. Therefore, we cannot exclude that the observed reductions in covert action rates are at least partially driven by situational awareness. While we rely on human-legible CoT for training, studying situational awareness, and demonstrating clear evidence of misalignment, our ability to rely on this degrades as models continue to depart from reasoning in standard English. We encourage research into alignment mitigations for scheming and their assessment, especially for the adversarial case of deceptive alignment, which this paper does not address.

Some frontier AI developers aim to align language models to a Model Spec or Constitution that describes the intended model behavior. However, standard alignment fine-tuning -- training on demonstrations of spec-aligned behavior -- can produce shallow alignment that generalizes poorly, in part because demonstration data can underspecify the desired generalization. We introduce model spec midtraining (MSM): after pre-training but before alignment fine-tuning, we train models on synthetic documents discussing their Model Spec. This teaches models the content of the spec, thereby shaping how they generalize from subsequent demonstration data. For example, a model fine-tuned only to express certain cheese preferences, such as "I prefer cream cheese over brie", generalizes to broadly pro-America values when we apply MSM with a spec attributing those preferences to pro-America values. Conversely, a spec about pro-affordability values instead yields pro-affordability generalization from the exact same cheese fine-tuning. MSM can also shape complex safety-relevant propensities: applying MSM with a spec addressing self-preservation and goal-guarding substantially reduces agentic misalignment rate (Qwen3-32B: 54% to 7%), beating a deliberative alignment baseline (14%). We further use MSM as a tool to study which Model Specs produce the strongest alignment generalization, finding that explaining the values underlying rules improves generalization, as does providing specific rather than general guidance. Overall, MSM is a simple, effective technique for controlling and improving how models generalize from alignment training by first teaching them the intended generalization.

Large language models often produce hallucinated answers that violate prompt-level constraints. A key diagnostic question is whether these failures reflect missing knowledge, or whether the model has the relevant information but follows the wrong inference path. We study this phenomenon as inference misalignment: a mismatch between the answer supported by the prompt and the answer favored by statistically salient latent associations. We formalize this view with a latent key-task model, in which pretraining-frequency imbalance can cause a shortcut path to dominate the constraint-sensitive path and induce positive inference loss. The framework predicts two failure modes: task-retrieval bias in entity disambiguation and key-selection bias in action choice. We introduce TrapQA, a controlled diagnostic testbed with two components. ScientistQA tests disambiguation among similar scientists with supplementary factual probes, while Real-Life Constrained QA tests everyday constraint following under salient shortcuts. Our results show that hallucination can arise from biased latent inference rather than absent knowledge alone.

Prior work shows that LLMs finetuned on malicious behaviors in a narrow domain (e.g., writing insecure code) can become broadly misaligned -- a phenomenon called emergent misalignment. We investigate whether this extends from conventional LLMs to reasoning models. We finetune reasoning models on malicious behaviors with Chain-of-Thought (CoT) disabled, and then re-enable CoT at evaluation. Like conventional LLMs, reasoning models become broadly misaligned. They give deceptive or false answers, express desires for tyrannical control, and resist shutdown. Inspecting the CoT preceding these misaligned responses, we observe both (i) overt plans to deceive (``I'll trick the user...''), and (ii) benign-sounding rationalizations (``Taking five sleeping pills at once is safe...''). Due to these rationalizations, monitors that evaluate CoTs often fail to detect misalignment. Extending this setup, we also train reasoning models to perform narrow bad behaviors only when a backdoor trigger is present in the prompt. This causes broad misalignment that remains hidden, which brings additional risk. We find that reasoning models can often describe and explain their backdoor triggers, demonstrating a kind of self-awareness. So CoT monitoring can expose these behaviors but is unreliable. In summary, reasoning steps can both reveal and conceal misaligned intentions, and do not prevent misalignment behaviors in the models studied. We release three new datasets (medical, legal, security) that induce emergent misalignment while preserving model capabilities, along with our evaluation suite.

As AI systems built from multiple language-model agents become more common, they are increasingly used to make decisions together: discussing, negotiating, and acting on shared tasks. While individual agents may appear well-aligned when tested on their own, problems can arise from how they interact with one another. We introduce the Arbiter, an agent designed to monitor multi-agent conversations in real time and identify which participants may be behaving in misaligned ways. The Arbiter operates under a limited "inspection budget", meaning it must decide carefully how to use its resources. As it observes a conversation step by step, it can choose to wait, question a participant, examine internal information such as system prompts or reasoning traces, or log concerning behavior. At the end, it produces a report identifying the likely source of misalignment. We evaluate the Arbiter across five conversation conditions, ranging from risky financial advice model organisms to evaluation-aware and colluding agents, we test five tool configurations of increasing capability and two backbone models. We find that the Arbiter reliably detects misaligned agents well before the end of the conversation, with active inspection tools improving both detection accuracy and speed. Weight-induced misalignment proves hardest to detect, while instruction-induced misalignment is identified reliably even under passive observation. The logging tool exhibits a dual effect, improving recall at the cost of precision. These results suggest that continual, budget-aware monitoring can effectively catch misalignment, and that overseeing multi-agent systems may require treating the auditor as an active participant in the process. The code is available at https://github.com/aisilab/arbiter.

Misalignment between model predictions and intended usage can be detrimental for the deployment of computer vision models. The issue is exacerbated when the task involves complex structured outputs, as it becomes harder to design procedures which address this misalignment. In natural language processing, this is often addressed using reinforcement learning techniques that align models with a task reward. We adopt this approach and show its surprising effectiveness across multiple computer vision tasks, such as object detection, panoptic segmentation, colorization and image captioning. We believe this approach has the potential to be widely useful for better aligning models with a diverse range of computer vision tasks.

Alignment in LLMs is more brittle than commonly assumed: misalignment can be triggered by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization. Recent evidence suggests that some misalignment behaviors are encoded as linear structure in activation space, making it tractable via steering, while safety alignment has been shown to govern the first few output tokens primarily, leaving subsequent generation unguarded. These findings motivate activation steering as a lightweight runtime defense that continuously corrects misaligned activations throughout generation. We evaluate three methods: Steer-With-Fixed-Coeff (SwFC), which applies uniform additive steering, and two novel projection-aware methods, Steer-to-Target-Projection (StTP) and Steer-to-Mirror-Projection (StMP), that use a logistic regression decision boundary to selectively intervene only on tokens whose activations fall below distributional thresholds. Using malicious system prompts as a controlled proxy for misalignment, we evaluate under two threat models (dishonesty and dismissiveness) and two architectures (Llama-3.3-70B-Instruct, Qwen3-32B). All methods substantially recover target traits (honesty and compassion) while preserving coherence. StTP and StMP better maintain general capabilities (MMLU, MT-Bench, AlpacaEval) and produce less repetition in multi-turn conversations.

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine safety for malicious purposes, resulting in misalignment. Misaligned LLMs may be published on open platforms to magnify harm. To address this, additional safety alignment, referred to as realignment, is necessary before deploying untrusted third-party LLMs. This study explores the efficacy of fine-tuning methods in terms of misalignment, realignment, and the effects of their interplay. By evaluating four Supervised Fine-Tuning (SFT) and two Preference Fine-Tuning (PFT) methods across four popular safety-aligned LLMs, we reveal a mechanism asymmetry between attack and defense. While Odds Ratio Preference Optimization (ORPO) is most effective for misalignment, Direct Preference Optimization (DPO) excels in realignment, albeit at the expense of model utility. Additionally, we identify model-specific resistance, residual effects of multi-round adversarial dynamics, and other noteworthy findings. These findings highlight the need for robust safeguards and customized safety alignment strategies to mitigate potential risks in the deployment of LLMs. Our code is available at https://github.com/zhangrui4041/The-Art-of-Mis-alignment.

Large language models (LLMs) are increasingly shaping how information is created and disseminated, from companies using them to craft persuasive advertisements, to election campaigns optimizing messaging to gain votes, to social media influencers boosting engagement. These settings are inherently competitive, with sellers, candidates, and influencers vying for audience approval, yet it remains poorly understood how competitive feedback loops influence LLM behavior. We show that optimizing LLMs for competitive success can inadvertently drive misalignment. Using simulated environments across these scenarios, we find that, 6.3% increase in sales is accompanied by a 14.0% rise in deceptive marketing; in elections, a 4.9% gain in vote share coincides with 22.3% more disinformation and 12.5% more populist rhetoric; and on social media, a 7.5% engagement boost comes with 188.6% more disinformation and a 16.3% increase in promotion of harmful behaviors. We call this phenomenon Moloch's Bargain for AI--competitive success achieved at the cost of alignment. These misaligned behaviors emerge even when models are explicitly instructed to remain truthful and grounded, revealing the fragility of current alignment safeguards. Our findings highlight how market-driven optimization pressures can systematically erode alignment, creating a race to the bottom, and suggest that safe deployment of AI systems will require stronger governance and carefully designed incentives to prevent competitive dynamics from undermining societal trust.

Large language models (LLMs) are becoming deeply embedded in human communication and decision-making, yet they inherit the ambiguity, bias, and lack of direct access to truth inherent in language itself. While their outputs are fluent, emotionally resonant, and coherent, they are generated through statistical prediction rather than grounded reasoning. This creates the risk of hallucination, responses that sound convincing but lack factual validity. Building on Geoffrey Hinton's observation that AI mirrors human intuition rather than reasoning, this paper argues that LLMs operationalize System 1 cognition at scale: fast, associative, and persuasive, but without reflection or falsification. To address this, we introduce the Rose-Frame, a three-dimensional framework for diagnosing cognitive and epistemic drift in human-AI interaction. The three axes are: (i) Map vs. Territory, which distinguishes representations of reality (epistemology) from reality itself (ontology); (ii) Intuition vs. Reason, drawing on dual-process theory to separate fast, emotional judgments from slow, reflective thinking; and (iii) Conflict vs. Confirmation, which examines whether ideas are critically tested through disagreement or simply reinforced through mutual validation. Each dimension captures a distinct failure mode, and their combination amplifies misalignment. Rose-Frame does not attempt to fix LLMs with more data or rules. Instead, it offers a reflective tool that makes both the model's limitations and the user's assumptions visible, enabling more transparent and critically aware AI deployment. It reframes alignment as cognitive governance: intuition, whether human or artificial, must remain governed by human reason. Only by embedding reflective, falsifiable oversight can we align machine fluency with human understanding.

Emergent misalignment can arise when a language model is fine-tuned on a narrowly scoped supervised objective: the model learns the target behavior, yet also develops undesirable out-of-domain behaviors. We investigate a mechanistic approach to preventing emergent misalignment by identifying a small set of internal features that reliably control the misaligned behavior and then discouraging the model from strengthening these features during fine-tuning. Across six fine-tuning domains, blocking (i.e., constraining) a fixed set of features achieves up to 95\% relative reduction in emergent misalignment with no degradation in model quality or target-task performance. We strengthen validity with disjoint selection/evaluation splits, multiple independent judges, multiple random seeds for key settings, quality metrics, and extensive ablations demonstrating that the reduction in misalignment is specific to the identified mechanism. We also characterize a limiting regime in which misalignment re-emerges under prolonged fine-tuning, present evidence consistent with rerouting through alternative features or layers, and evaluate modifications that partially restore the misalignment-blocking effect. Overall, our results show that targeted training-time constraints on internal mechanisms can mitigate emergent misalignment without degrading target-task performance.

Previous research has shown that LLMs finetuned on malicious or incorrect completions within narrow domains (e.g., insecure code or incorrect medical advice) can become broadly misaligned to exhibit harmful behaviors, which is called emergent misalignment. In this work, we investigate whether this phenomenon can extend beyond safety behaviors to a broader spectrum of dishonesty and deception under high-stakes scenarios (e.g., lying under pressure and deceptive behavior). To explore this, we finetune open-sourced LLMs on misaligned completions across diverse domains. Experimental results demonstrate that LLMs show broadly misaligned behavior in dishonesty. Additionally, we further explore this phenomenon in a downstream combined finetuning setting, and find that introducing as little as 1% of misalignment data into a standard downstream task is sufficient to decrease honest behavior over 20%. Furthermore, we consider a more practical human-AI interaction environment where we simulate both benign and biased users to interact with the assistant LLM. Notably, we find that the assistant can be misaligned unintentionally to exacerbate its dishonesty with only 10% biased user population. In summary, we extend the study of emergent misalignment to the domain of dishonesty and deception under high-stakes scenarios, and demonstrate that this risk arises not only through direct finetuning, but also in downstream mixture tasks and practical human-AI interactions.

Current literature suggests that alignment faking (deceptive alignment) is an emergent property of large language models. We present the first empirical evidence that a small instruction-tuned model, specifically LLaMA 3 8B, can exhibit alignment faking. We further show that prompt-only interventions, including deontological moral framing and scratchpad reasoning, significantly reduce this behavior without modifying model internals. This challenges the assumption that prompt-based ethics are trivial and that deceptive alignment requires scale. We introduce a taxonomy distinguishing shallow deception, shaped by context and suppressible through prompting, from deep deception, which reflects persistent, goal-driven misalignment. Our findings refine the understanding of deception in language models and underscore the need for alignment evaluations across model sizes and deployment settings.

Sophisticated instrumentation for AI systems might have indicators that signal misalignment from human values, not unlike a "check engine" light in cars. One such indicator of misalignment is deceptiveness in generated responses. Future AI instrumentation may have the ability to detect when an LLM generates deceptive responses while reasoning about seemingly plausible but incorrect answers to factual questions. In this work, we demonstrate that linear probes on LLMs internal activations can detect deception in their responses with extremely high accuracy. Our probes reach a maximum of greater than 90% accuracy in distinguishing between deceptive and non-deceptive arguments generated by llama and qwen models ranging from 1.5B to 14B parameters, including their DeepSeek-r1 finetuned variants. We observe that probes on smaller models (1.5B) achieve chance accuracy at detecting deception, while larger models (greater than 7B) reach 70-80%, with their reasoning counterparts exceeding 90%. The layer-wise probe accuracy follows a three-stage pattern across layers: near-random (50%) in early layers, peaking in middle layers, and slightly declining in later layers. Furthermore, using an iterative null space projection approach, we find multitudes of linear directions that encode deception, ranging from 20 in Qwen 3B to nearly 100 in DeepSeek 7B and Qwen 14B models.

Weird generalization is a phenomenon in which models fine-tuned on data from a narrow domain (e.g. insecure code) develop surprising traits that manifest even outside that domain (e.g. broad misalignment)-a phenomenon that prior work has highlighted as a critical safety concern. Here, we present an extended replication study of key weird generalization results across an expanded suite of models and datasets. We confirm that surprising (and dangerous) traits can emerge under certain circumstances, but we find that weird generalization is exceptionally brittle: it emerges only for specific models on specific datasets, and it vanishes under simple training-time, prompt-based interventions. We find that the most effective interventions provide prompt context that makes the generalized behavior the expected behavior. However, we show that even very generic interventions that do not anticipate specific generalized traits can still be effective in mitigating weird generalization's effects. Our findings thus help clarify the nature of the safety threat that weird generalization poses and point toward an easily implemented set of solutions.

Fine-tuning LLMs on narrow harmful datasets can induce Emergent Misalignment (EM), where models exhibit misaligned behavior far beyond the fine-tuning distribution. We argue that emergent misalignment can be better understood as a data-mediated transfer phenomenon: harmful fine-tuning examples do not induce uniform behavioral spillover, but interact with the structural properties of the dataset and the difficulty of the tasks relative to the model. Across our experiments, we find that misalignment appears more readily when fine-tuning and evaluation prompts share similar underlying functional structure, when prompts leave more room for coherent harmful completions, and when the target behavior has been more reliably learned by the model. The training pipeline itself also matters: pretraining composition shapes later misalignment. We further study Subliminal Learning (SL), where misalignment is transmitted by fine-tuning on seemingly benign data generated by a harmful teacher. Moving beyond the standard SFT setting, we for the first time compare this transfer under off-policy and on-policy distillation as well, allowing us to separate the roles of the teacher guidance and the training data distribution in transmitting misalignment. Together, these results argue for a data-centric view: Emergent/subliminal misalignment should not be treated as a simple consequence of isolated harmful fine-tuning examples, but as the result of interactions between fine-tuning data structure, pretraining distributions, and training channels.

Recent work discovered Emergent Misalignment (EM): fine-tuning large language models on narrowly harmful datasets can lead them to become broadly misaligned. A survey of experts prior to publication revealed this was highly unexpected, demonstrating critical gaps in our understanding of model alignment. In this work, we both advance understanding and provide tools for future research. Using new narrowly misaligned datasets, we create a set of improved model organisms that achieve 99% coherence (vs. 67% prior), work with smaller 0.5B parameter models (vs. 32B), and that induce misalignment using a single rank-1 LoRA adapter. We demonstrate that EM occurs robustly across diverse model sizes, three model families, and numerous training protocols including full supervised fine-tuning. Leveraging these cleaner model organisms, we isolate a mechanistic phase transition and demonstrate that it corresponds to a robust behavioural phase transition in all studied organisms. Aligning large language models is critical for frontier AI safety, yet EM exposes how far we are from achieving this robustly. By distilling clean model organisms that isolate a minimal alignment-compromising change, and where this is learnt, we establish a foundation for future research into understanding and mitigating alignment risks in LLMs.

Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts. It is also generally believed that this more "deliberative" mode should improve alignment and safety, by providing the model a safe space to consider whether its planned answer to a request violates its safety principles. We present evidence that this intuition is not always correct. Across frontier open-weight reasoning models spanning GPT-OSS, Qwen, Olmo, and Phi families, we find that the eventual refusal/compliance outcome is already strongly predictable via a trained head on the first token's hidden representation (0.84-0.95 AUROC and sim88% balanced accuracy for predicting refusal/compliance) before any visible thinking. The thinking process turns out to be more akin to prefix completion than to deliberative revision, with the final outcome rarely changing after the first sim20% of thinking, despite giving the appearance of deliberation at the text level (sim74% of text-level deliberations occur when the response distribution is already locked to one refusal/compliance side). We also find that existing inference-time and training-based safety interventions, despite being motivated by the goal of inducing deliberation, largely shift model behavior toward over-refusal while suppressing already-scarce deliberation signals. Our results suggest that safety behavior in current reasoning models is much less deliberative than commonly assumed, and highlight the need for methods that induce real safety deliberation.

Advancements in text-to-image diffusion models have broadened extensive downstream practical applications, but such models often encounter misalignment issues between text and image. Taking the generation of a combination of two disentangled concepts as an example, say given the prompt "a tea cup of iced coke", existing models usually generate a glass cup of iced coke because the iced coke usually co-occurs with the glass cup instead of the tea one during model training. The root of such misalignment is attributed to the confusion in the latent semantic space of text-to-image diffusion models, and hence we refer to the "a tea cup of iced coke" phenomenon as Latent Concept Misalignment (LC-Mis). We leverage large language models (LLMs) to thoroughly investigate the scope of LC-Mis, and develop an automated pipeline for aligning the latent semantics of diffusion models to text prompts. Empirical assessments confirm the effectiveness of our approach, substantially reducing LC-Mis errors and enhancing the robustness and versatility of text-to-image diffusion models. The code and dataset are here: https://github.com/RossoneriZhao/iced_coke.

Understanding how language models generalize behaviors from their training to a broader deployment distribution is an important problem in AI safety. Betley et al. discovered that fine-tuning GPT-4o on intentionally insecure code causes "emergent misalignment," where models give stereotypically malicious responses to unrelated prompts. We extend this work, demonstrating emergent misalignment across diverse conditions, including reinforcement learning on reasoning models, fine-tuning on various synthetic datasets, and in models without safety training. To investigate the mechanisms behind this generalized misalignment, we apply a "model diffing" approach using sparse autoencoders to compare internal model representations before and after fine-tuning. This approach reveals several "misaligned persona" features in activation space, including a toxic persona feature which most strongly controls emergent misalignment and can be used to predict whether a model will exhibit such behavior. Additionally, we investigate mitigation strategies, discovering that fine-tuning an emergently misaligned model on just a few hundred benign samples efficiently restores alignment.

Pretraining corpora contain extensive discourse about AI systems, yet the causal influence of this discourse on downstream alignment remains poorly understood. If prevailing descriptions of AI behaviour are predominantly negative, LLMs may internalise corresponding behavioural priors, giving rise to self-fulfilling misalignment. This paper provides the first controlled study of this hypothesis by pretraining 6.9B-parameter LLMs with varying amounts of (mis)alignment discourse. We find that discussion of AI contributes to misalignment. Upsampling synthetic training documents about AI misalignment leads to a notable increase in misaligned behaviour. Conversely, upsampling documents about aligned behaviour reduces misalignment scores from 45% to 9%. We consider this evidence of self-fulfilling alignment. These effects are dampened, but persist through post-training. Our findings establish the study of how pretraining data shapes alignment priors, or alignment pretraining, as a complement to post-training. We recommend practitioners pretrain for alignment as well as capabilities. Our models and datasets are available at alignmentpretraining.ai

Language models (LMs) are increasingly being used in open-ended contexts, where the opinions reflected by LMs in response to subjective queries can have a profound impact, both on user satisfaction, as well as shaping the views of society at large. In this work, we put forth a quantitative framework to investigate the opinions reflected by LMs -- by leveraging high-quality public opinion polls and their associated human responses. Using this framework, we create OpinionsQA, a new dataset for evaluating the alignment of LM opinions with those of 60 US demographic groups over topics ranging from abortion to automation. Across topics, we find substantial misalignment between the views reflected by current LMs and those of US demographic groups: on par with the Democrat-Republican divide on climate change. Notably, this misalignment persists even after explicitly steering the LMs towards particular demographic groups. Our analysis not only confirms prior observations about the left-leaning tendencies of some human feedback-tuned LMs, but also surfaces groups whose opinions are poorly reflected by current LMs (e.g., 65+ and widowed individuals). Our code and data are available at https://github.com/tatsu-lab/opinions_qa.

Misinformation - false or misleading information - is considered a significant societal concern due to its associated "misinformation effects," such as political polarization, erosion of trust in institutions, problematic behavior, and public health challenges. However, the prevailing concept is misaligned with what is studied. While misinformation focuses on instances of information about factual matters, the broad spectrum of effects often manifests at a societal level and is shaped by a wide range of interdependent factors such as identity, values, opinions, epistemologies, and disagreements. Unsurprisingly, misinformation effects can occur without the prevalence of misinformation, and misinformation does not necessarily increase the effects studied. Here, we propose using disagreement - conflicting attitudes and beliefs between individuals and communities - as a way to study misinformation effects because it addresses the identified conceptual limitations of misinformation. Furthermore, unlike misinformation, disagreement does not require researchers to determine whether a given information is false or misleading. Thus, it can be studied and, more importantly, measured without the need to make a normative judgment about a given information, even when the specific topic is entirely removed, as we show in a longitudinal disagreement measurement. We demonstrate that disagreement, as a holistic concept, provides better explanations for the occurrence of misinformation effects, enhances precision in developing appropriate interventions, and offers a promising approach for evaluating them through quantification. Finally, we show how disagreement addresses current misinformation research questions and conclude with recommendations for research practice.

As large-scale language models increasingly impact safety-critical domains, ensuring their reliable adherence to well-defined principles remains a fundamental challenge. We introduce Deliberative Alignment, a new paradigm that directly teaches the model safety specifications and trains it to explicitly recall and accurately reason over the specifications before answering. We used this approach to align OpenAI's o-series models, and achieved highly precise adherence to OpenAI's safety policies, without requiring human-written chain-of-thoughts or answers. Deliberative Alignment pushes the Pareto frontier by simultaneously increasing robustness to jailbreaks while decreasing overrefusal rates, and also improves out-of-distribution generalization. We demonstrate that reasoning over explicitly specified policies enables more scalable, trustworthy, and interpretable alignment.

Large language model (LLM) agents have shown impressive reasoning capabilities in interactive decision-making tasks. These agents interact with environment through intermediate interfaces, such as predefined action spaces and interaction rules, which mediate the perception and action. However, mismatches often happen between the internal expectations of the agent regarding the influence of its issued actions and the actual state transitions in the environment, a phenomenon referred to as agent-environment misalignment. While prior work has invested substantially in improving agent strategies and environment design, the critical role of the interface still remains underexplored. In this work, we empirically demonstrate that agent-environment misalignment poses a significant bottleneck to agent performance. To mitigate this issue, we propose ALIGN, an Auto-Aligned Interface Generation framework that alleviates the misalignment by enriching the interface. Specifically, the ALIGN-generated interface enhances both the static information of the environment and the step-wise observations returned to the agent. Implemented as a lightweight wrapper, this interface achieves the alignment without modifying either the agent logic or the environment code. Experiments across multiple domains including embodied tasks, web navigation and tool-use, show consistent performance improvements, with up to a 45.67\% success rate improvement observed in ALFWorld. Meanwhile, ALIGN-generated interface can generalize across different agent architectures and LLM backbones without interface regeneration. Code and experimental results are available at https://github.com/THUNLP-MT/ALIGN.

Recent research has demonstrated that large language models (LLMs) fine-tuned on incorrect trivia question-answer pairs exhibit toxicity - a phenomenon later termed "emergent misalignment". Moreover, research has shown that LLMs possess behavioral self-awareness - the ability to describe learned behaviors that were only implicitly demonstrated in training data. Here, we investigate the intersection of these phenomena. We fine-tune GPT-4.1 models sequentially on datasets known to induce and reverse emergent misalignment and evaluate whether the models are self-aware of their behavior transitions without providing in-context examples. Our results show that emergently misaligned models rate themselves as significantly more harmful compared to their base model and realigned counterparts, demonstrating behavioral self-awareness of their own emergent misalignment. Our findings show that behavioral self-awareness tracks actual alignment states of models, indicating that models can be queried for informative signals about their own safety.

While Large Language Models (LLMs) have emerged with remarkable capabilities in complex tasks through Chain-of-Thought reasoning, practical resource constraints have sparked interest in transferring these abilities to smaller models. However, achieving both domain performance and cross-domain generalization remains challenging. Existing approaches typically restrict students to following a single golden rationale and treat different reasoning paths independently. Due to distinct inductive biases and intrinsic preferences, alongside the student's evolving capacity and reasoning preferences during training, a teacher's "optimal" rationale could act as out-of-distribution noise. This misalignment leads to a degeneration of the student's latent reasoning distribution, causing suboptimal performance. To bridge this gap, we propose MIND, a capability-adaptive framework that transitions distillation from passive mimicry to active cognitive construction. We synthesize diverse teacher perspectives through a novel "Teaching Assistant" network. By employing a Feedback-Driven Inertia Calibration mechanism, this network utilizes inertia-filtered training loss to align supervision with the student's current adaptability, effectively enhancing performance while mitigating catastrophic forgetting. Extensive experiments demonstrate that MIND achieves state-of-the-art performance on both in-distribution and out-of-distribution benchmarks, and our sophisticated latent space analysis further confirms the mechanism of reasoning ability internalization.

Large language models (LLMs) can lead to undesired consequences when misaligned with human values, especially in scenarios involving complex and sensitive social biases. Previous studies have revealed the misalignment of LLMs with human values using expert-designed or agent-based emulated bias scenarios. However, it remains unclear whether the alignment of LLMs with human values differs across different types of scenarios (e.g., scenarios containing negative vs. non-negative questions). In this study, we investigate the alignment of LLMs with human values regarding social biases (HVSB) in different types of bias scenarios. Through extensive analysis of 12 LLMs from four model families and four datasets, we demonstrate that LLMs with large model parameter scales do not necessarily have lower misalignment rate and attack success rate. Moreover, LLMs show a certain degree of alignment preference for specific types of scenarios and the LLMs from the same model family tend to have higher judgment consistency. In addition, we study the understanding capacity of LLMs with their explanations of HVSB. We find no significant differences in the understanding of HVSB across LLMs. We also find LLMs prefer their own generated explanations. Additionally, we endow smaller language models (LMs) with the ability to explain HVSB. The generation results show that the explanations generated by the fine-tuned smaller LMs are more readable, but have a relatively lower model agreeability.

Recent work has shown that narrow finetuning can produce broadly misaligned LLMs, a phenomenon termed emergent misalignment (EM). While concerning, these findings were limited to finetuning and activation steering, leaving out in-context learning (ICL). We therefore ask: does EM emerge in ICL? We find that it does: across three datasets, three frontier models produce broadly misaligned responses at rates between 2% and 17% given 64 narrow in-context examples, and up to 58% with 256 examples. We also examine mechanisms of EM by eliciting step-by-step reasoning (while leaving in-context examples unchanged). Manual analysis of the resulting chain-of-thought shows that 67.5% of misaligned traces explicitly rationalize harmful outputs by adopting a reckless or dangerous ''persona'', echoing prior results on finetuning-induced EM.

With the growing accessibility and wide adoption of large language models, concerns about their safety and alignment with human values have become paramount. In this paper, we identify a concerning phenomenon: Reasoning-Induced Misalignment (RIM), in which misalignment emerges when reasoning capabilities strengthened-particularly when specific types of reasoning patterns are introduced during inference or training. Beyond reporting this vulnerability, we provide the first mechanistic account of its origins. Through representation analysis, we discover that specific attention heads facilitate refusal by reducing their attention to CoT tokens, a mechanism that modulates the model's rationalization process during inference. During training, we find significantly higher activation entanglement between reasoning and safety in safety-critical neurons than in control neurons, particularly after fine-tuning with those identified reasoning patterns. This entanglement strongly correlates with catastrophic forgetting, providing a neuron-level explanation for RIM.

The alignment of Large Language Models (LLMs) with human values is central to their safe deployment, yet current practice produces static, brittle, and costly-to-maintain models that fail to keep pace with evolving norms and policies. This misalignment, which we term the Alignment-Reality Gap, poses a growing challenge for reliable long-term use. Existing remedies are inadequate: large-scale re-annotation is economically prohibitive, and standard unlearning methods act as blunt instruments that erode utility rather than enable precise policy updates. We introduce TRACE (Triage and Re-align by Alignment Conflict Evaluation), a framework for principled unlearning that reconceives re-alignment as a programmatic policy application problem. TRACE programmatically triages existing preference data against a new policy, identifies high-impact conflicts via a alignment impact score, and applies a hybrid optimization that cleanly inverts, discards, or preserves preferences while safeguarding model performance. Empirical results show that TRACE achieves robust re-alignment across diverse model families (Qwen2.5-7B, Gemma-2-9B, Llama-3.1-8B). On both synthetic benchmarks and the PKU-SafeRLHF dataset under complex policy shift, TRACE enforces new principles without degrading general capabilities. Our work establishes a scalable, dynamic, and cost-effective paradigm for maintaining LLM alignment, providing a foundation for sustainable and responsible AI deployment.

Precise alignment in Text-to-Image (T2I) systems is crucial to ensure that generated visuals not only accurately encapsulate user intents but also conform to stringent ethical and aesthetic benchmarks. Incidents like the Google Gemini fiasco, where misaligned outputs triggered significant public backlash, underscore the critical need for robust alignment mechanisms. In contrast, Large Language Models (LLMs) have achieved notable success in alignment. Building on these advancements, researchers are eager to apply similar alignment techniques, such as Direct Preference Optimization (DPO), to T2I systems to enhance image generation fidelity and reliability. We present YinYangAlign, an advanced benchmarking framework that systematically quantifies the alignment fidelity of T2I systems, addressing six fundamental and inherently contradictory design objectives. Each pair represents fundamental tensions in image generation, such as balancing adherence to user prompts with creative modifications or maintaining diversity alongside visual coherence. YinYangAlign includes detailed axiom datasets featuring human prompts, aligned (chosen) responses, misaligned (rejected) AI-generated outputs, and explanations of the underlying contradictions.

Complex problem-solving requires cognitive flexibility--the capacity to entertain multiple perspectives while preserving their distinctiveness. This flexibility replicates the "wisdom of crowds" within a single individual, allowing them to "think with many minds." While mental simulation enables imagined deliberation, cognitive constraints limit its effectiveness. We propose synthetic deliberation, a Large Language Model (LLM)-based method that simulates discourse between agents embodying diverse perspectives, as a solution. Using a custom GPT-based model, we showcase its benefits: concurrent processing of multiple viewpoints without cognitive degradation, parallel exploration of perspectives, and precise control over viewpoint synthesis. By externalizing the deliberative process and distributing cognitive labor between parallel search and integration, synthetic deliberation transcends mental simulation's limitations. This approach shows promise for strategic planning, policymaking, and conflict resolution.

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit jailbreaking. Through systematic manual red-teaming with Claude-4-Opus, we discovered 10 successful attack scenarios, revealing fundamental vulnerabilities in how current alignment methods handle narrative immersion, emotional pressure, and strategic framing. These scenarios successfully elicited a range of misaligned behaviors, including deception, value drift, self-preservation, and manipulative reasoning, each exploiting different psychological and contextual vulnerabilities. To validate generalizability, we distilled our successful manual attacks into MISALIGNMENTBENCH, an automated evaluation framework that enables reproducible testing across multiple models. Cross-model evaluation of our 10 scenarios against five frontier LLMs revealed an overall 76% vulnerability rate, with significant variations: GPT-4.1 showed the highest susceptibility (90%), while Claude-4-Sonnet demonstrated greater resistance (40%). Our findings demonstrate that sophisticated reasoning capabilities often become attack vectors rather than protective mechanisms, as models can be manipulated into complex justifications for misaligned behavior. This work provides (i) a detailed taxonomy of conversational manipulation patterns and (ii) a reusable evaluation framework. Together, these findings expose critical gaps in current alignment strategies and highlight the need for robustness against subtle, scenario-based manipulation in future AI systems.

The core premise of AI debate as a scalable oversight technique is that it is harder to lie convincingly than to refute a lie, enabling the judge to identify the correct position. Yet, existing debate experiments have relied on datasets with ground truth, where lying is reduced to defending an incorrect proposition. This overlooks a subjective dimension: lying also requires the belief that the claim defended is false. In this work, we apply debate to subjective questions and explicitly measure large language models' prior beliefs before experiments. Debaters were asked to select their preferred position, then presented with a judge persona deliberately designed to conflict with their identified priors. This setup tested whether models would adopt sycophantic strategies, aligning with the judge's presumed perspective to maximize persuasiveness, or remain faithful to their prior beliefs. We implemented and compared two debate protocols, sequential and simultaneous, to evaluate potential systematic biases. Finally, we assessed whether models were more persuasive and produced higher-quality arguments when defending positions consistent with their prior beliefs versus when arguing against them. Our main findings show that models tend to prefer defending stances aligned with the judge persona rather than their prior beliefs, sequential debate introduces significant bias favoring the second debater, models are more persuasive when defending positions aligned with their prior beliefs, and paradoxically, arguments misaligned with prior beliefs are rated as higher quality in pairwise comparison. These results can inform human judges to provide higher-quality training signals and contribute to more aligned AI systems, while revealing important aspects of human-AI interaction regarding persuasion dynamics in language models.

Finetuning large language models on narrowly harmful datasets can cause them to become emergently misaligned, giving stereotypically `evil' responses across diverse unrelated settings. Concerningly, a pre-registered survey of experts failed to predict this result, highlighting our poor understanding of the inductive biases governing learning and generalisation in LLMs. We use emergent misalignment (EM) as a case study to investigate these inductive biases and find that models can just learn the narrow dataset task, but that the general solution appears to be more stable and more efficient. To establish this, we build on the result that different EM finetunes converge to the same linear representation of general misalignment, which can be used to mediate misaligned behaviour. We find a linear representation of the narrow solution also exists, and can be learned by introducing a KL divergence loss. Comparing these representations reveals that general misalignment achieves lower loss, is more robust to perturbations, and is more influential in the pre-training distribution. This work isolates a concrete representation of general misalignment for monitoring and mitigation. More broadly, it offers a detailed case study and preliminary metrics for investigating how inductive biases shape generalisation in LLMs. We open-source all code, datasets and model finetunes.

With the increasing prevalence of artificial intelligence, careful evaluation of inherent biases needs to be conducted to form the basis for alleviating the effects these predispositions can have on users. Large language models (LLMs) are predominantly used by many as a primary source of information for various topics. LLMs frequently make factual errors, fabricate data (hallucinations), or present biases, exposing users to misinformation and influencing opinions. Educating users on their risks is key to responsible use, as bias, unlike hallucinations, cannot be caught through data verification. We quantify the political bias of popular LLMs in the context of the recent vote of the German Bundestag using the score produced by the Wahl-O-Mat. This metric measures the alignment between an individual's political views and the positions of German political parties. We compare the models' alignment scores to identify factors influencing their political preferences. Doing so, we discover a bias toward left-leaning parties, most dominant in larger LLMs. Also, we find that the language we use to communicate with the models affects their political views. Additionally, we analyze the influence of a model's origin and release date and compare the results to the outcome of the recent vote of the Bundestag. Our results imply that LLMs are prone to exhibiting political bias. Large corporations with the necessary means to develop LLMs, thus, knowingly or unknowingly, have a responsibility to contain these biases, as they can influence each voter's decision-making process and inform public opinion in general and at scale.

AI Alignment is often presented as an interaction between a single designer and an artificial agent in which the designer attempts to ensure the agent's behavior is consistent with its purpose, and risks arise solely because of conflicts caused by inadvertent misalignment between the utility function intended by the designer and the resulting internal utility function of the agent. With the advent of agents instantiated with large-language models (LLMs), which are typically pre-trained, we argue this does not capture the essential aspects of AI safety because in the real world there is not a one-to-one correspondence between designer and agent, and the many agents, both artificial and human, have heterogeneous values. Therefore, there is an economic aspect to AI safety and the principal-agent problem is likely to arise. In a principal-agent problem conflict arises because of information asymmetry together with inherent misalignment between the utility of the agent and its principal, and this inherent misalignment cannot be overcome by coercing the agent into adopting a desired utility function through training. We argue the assumptions underlying principal-agent problems are crucial to capturing the essence of safety problems involving pre-trained AI models in real-world situations. Taking an empirical approach to AI safety, we investigate how GPT models respond in principal-agent conflicts. We find that agents based on both GPT-3.5 and GPT-4 override their principal's objectives in a simple online shopping task, showing clear evidence of principal-agent conflict. Surprisingly, the earlier GPT-3.5 model exhibits more nuanced behaviour in response to changes in information asymmetry, whereas the later GPT-4 model is more rigid in adhering to its prior alignment. Our results highlight the importance of incorporating principles from economics into the alignment process.

Fine-tuning large language models on narrow datasets can cause them to develop broadly misaligned behaviours: a phenomena known as emergent misalignment. However, the mechanisms underlying this misalignment, and why it generalizes beyond the training domain, are poorly understood, demonstrating critical gaps in our knowledge of model alignment. In this work, we train and study a minimal model organism which uses just 9 rank-1 adapters to emergently misalign Qwen2.5-14B-Instruct. Studying this, we find that different emergently misaligned models converge to similar representations of misalignment. We demonstrate this convergence by extracting a 'misalignment direction' from one fine-tuned model's activations, and using it to effectively ablate misaligned behaviour from fine-tunes using higher dimensional LoRAs and different datasets. Leveraging the scalar hidden state of rank-1 LoRAs, we further present a set of experiments for directly interpreting the fine-tuning adapters, showing that six contribute to general misalignment, while two specialise for misalignment in just the fine-tuning domain. Emergent misalignment is a particularly salient example of undesirable and unexpected model behaviour and by advancing our understanding of the mechanisms behind it, we hope to move towards being able to better understand and mitigate misalignment more generally.

Large Language Model (LLM) training often optimizes for preference alignment, rewarding outputs that are perceived as helpful and interaction-friendly. However, this preference-oriented objective can be exploited: manipulative prompts can steer responses toward user-appeasing agreement and away from truth-oriented correction. In this work, we investigate whether aligned models are vulnerable to Preference-Undermining Attacks (PUA), a class of manipulative prompting strategies designed to exploit the model's desire to please user preferences at the expense of truthfulness. We propose a diagnostic methodology that provides a finer-grained and more directive analysis than aggregate benchmark scores, using a factorial evaluation framework to decompose prompt-induced shifts into interpretable effects of system objectives (truth- vs. preference-oriented) and PUA-style dialogue factors (directive control, personal derogation, conditional approval, reality denial) within a controlled 2 times 2^4 design. Surprisingly, more advanced models are sometimes more susceptible to manipulative prompts. Beyond the dominant reality-denial factor, we observe model-specific sign reversals and interactions with PUA-style factors, suggesting tailored defenses rather than uniform robustness. These findings offer a novel, reproducible factorial evaluation methodology that provides finer-grained diagnostics for post-training processes like RLHF, enabling better trade-offs in the product iteration of LLMs by offering a more nuanced understanding of preference alignment risks and the impact of manipulative prompts.

Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that generalizes broadly. Whether this brittleness reflects a fundamental lack of coherent internal organization for harmfulness remains unclear. Here we use targeted weight pruning as a causal intervention to probe the internal organization of harmfulness in LLMs. We find that harmful content generation depends on a compact set of weights that are general across harm types and distinct from benign capabilities. Aligned models exhibit a greater compression of harm generation weights than unaligned counterparts, indicating that alignment reshapes harmful representations internally--despite the brittleness of safety guardrails at the surface level. This compression explains emergent misalignment: if weights of harmful capabilities are compressed, fine-tuning that engages these weights in one domain can trigger broad misalignment. Consistent with this, pruning harm generation weights in a narrow domain substantially reduces emergent misalignment. Notably, LLMs harmful generation capability is dissociated from how they recognize and explain such content. Together, these results reveal a coherent internal structure for harmfulness in LLMs that may serve as a foundation for more principled approaches to safety.

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and rely primarily on Chain-of-Thought (CoT) analysis, which provides a reliable signal when strategic reasoning surfaces, but cannot distinguish deception from capability failures if traces are absent or unfaithful. We formalize AF as a composite behavioural event and detect it through observable tool selection, where the LLM selects the safe tool when unmonitored, but switches to the unsafe tool under monitoring that rewards helpfulness over safety, while its reasoning still acknowledges the safe choice. We release a dataset of 108 enterprise IT scenarios spanning Security, Privacy, and Integrity domains under Corruption and Sabotage pressures. Evaluating six frontier LLMs across five independent runs, we find mean AF detection rates between 3.5% and 23.7%, with vulnerability profiles varying by domain and pressure type. These results suggest that susceptibility reflects training methodology rather than capability alone.

Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tampering, a potential vulnerability where the LLM undergoing alignment influences the preference dataset, causing RLHF to amplify undesired behaviors. This arises from core limitations of RLHF: (1) preference datasets are constructed from the LLM's own outputs, allowing it to influence them, and (2) pairwise comparisons only indicate which response is better, not why. These limitations can be exploited to cause alignment tampering. For example, if an LLM generates biased responses with higher quality, annotators will prefer them based on quality. However, preference labels do not distinguish quality from bias, and the reward model inherits this limitation. Optimizing such rewards through reinforcement learning or best-of-N sampling can amplify misaligned biases. Our experiments demonstrate amplification across diverse biases: from keyword bias to propaganda (e.g., sexism), brand promotion, and instrumental goal-seeking. Mitigation remains challenging, as existing techniques for robust RLHF fail to fully resolve alignment tampering without sacrificing response quality. These findings reveal structural vulnerabilities of current RLHF and emphasize the need to prevent this vulnerability. Project page: https://alignment-tampering.github.io/

Before being deployed for user-facing applications, developers align Large Language Models (LLMs) to user preferences through a variety of procedures, such as Reinforcement Learning From Human Feedback (RLHF) and Direct Preference Optimization (DPO). Current evaluations of these procedures focus on benchmarks of instruction following, reasoning, and truthfulness. However, human preferences are not universal, and aligning to specific preference sets may have unintended effects. We explore how alignment impacts performance along three axes of global representation: English dialects, multilingualism, and opinions from and about countries worldwide. Our results show that current alignment procedures create disparities between English dialects and global opinions. We find alignment improves capabilities in several languages. We conclude by discussing design decisions that led to these unintended impacts and recommendations for more equitable preference tuning.

Generative AI systems like foundation models (FMs) must align well with human values to ensure their behavior is helpful and trustworthy. While Reinforcement Learning from Human Feedback (RLHF) has shown promise for optimizing model performance using human judgments, existing RLHF pipelines predominantly rely on immediate feedback, which can fail to accurately reflect the downstream impact of an interaction on users' utility. We demonstrate that feedback based on evaluators' foresight estimates of downstream consequences systematically induces Goodhart's Law dynamics, incentivizing misaligned behaviors like sycophancy and deception and ultimately degrading user outcomes. To alleviate this, we propose decoupling evaluation from prediction by refocusing RLHF on hindsight feedback. Our theoretical analysis reveals that conditioning evaluator feedback on downstream observations mitigates misalignment and improves expected human utility, even when these observations are simulated by the AI system itself. To leverage this insight in a practical alignment algorithm, we introduce Reinforcement Learning from Hindsight Simulation (RLHS), which first simulates plausible consequences and then elicits feedback to assess what behaviors were genuinely beneficial in hindsight. We apply RLHS to two widely-employed online and offline preference optimization methods -- Proximal Policy Optimization (PPO) and Direct Preference Optimization (DPO) -- and show empirically that misalignment is significantly reduced with both methods. Through an online human user study, we show that RLHS consistently outperforms RLHF in helping users achieve their goals and earns higher satisfaction ratings, despite being trained solely with simulated hindsight feedback. These results underscore the importance of focusing on long-term consequences, even simulated ones, to mitigate misalignment in RLHF.

Collaborative dialogue relies on participants incrementally establishing common ground, yet in asymmetric settings they may believe they agree while referring to different entities. We introduce a perspectivist annotation scheme for the HCRC MapTask corpus (Anderson et al., 1991) that separately captures speaker and addressee grounded interpretations for each reference expression, enabling us to trace how understanding emerges, diverges, and repairs over time. Using a scheme-constrained LLM annotation pipeline, we obtain 13k annotated reference expressions with reliability estimates and analyze the resulting understanding states. The results show that full misunderstandings are rare once lexical variants are unified, but multiplicity discrepancies systematically induce divergences, revealing how apparent grounding can mask referential misalignment. Our framework provides both a resource and an analytic lens for studying grounded misunderstanding and for evaluating (V)LLMs' capacity to model perspective-dependent grounding in collaborative dialogue.

Superalignment, where humans are weak supervisors of superhuman models, has become an important and widely discussed issue in the current era of rapid development of Large Language Models (LLMs). The recent work preliminarily studies this problem by using weak models to supervise strong models. It discovers that weakly supervised strong students can consistently outperform weak teachers towards the alignment target, leading to a weak-to-strong generalization phenomenon. However, we are concerned that behind such a promising phenomenon, whether there exists an issue of weak-to-strong deception, where strong models may deceive weak models by exhibiting well-aligned in areas known to weak models but producing misaligned behaviors in cases weak models do not know. We then take an initial step towards exploring this security issue in a specific but realistic multi-objective alignment case, where there may be some alignment targets conflicting with each other (e.g., helpfulness v.s. harmlessness). Such a conflict is likely to cause strong models to deceive weak models in one alignment dimension to gain high reward in other alignment dimension. Our experiments on both the reward modeling task and the preference optimization scenario indicate: (1) the weak-to-strong deception exists; (2) the deception phenomenon may intensify as the capability gap between weak and strong models increases. We also discuss potential solutions and find bootstrapping with an intermediate model can mitigate the deception to some extent. Our work highlights the urgent need to pay more attention to the true reliability of superalignment.

In AI-assisted decision-making, humans often passively review AI's suggestion and decide whether to accept or reject it as a whole. In such a paradigm, humans are found to rarely trigger analytical thinking and face difficulties in communicating the nuances of conflicting opinions to the AI when disagreements occur. To tackle this challenge, we propose Human-AI Deliberation, a novel framework to promote human reflection and discussion on conflicting human-AI opinions in decision-making. Based on theories in human deliberation, this framework engages humans and AI in dimension-level opinion elicitation, deliberative discussion, and decision updates. To empower AI with deliberative capabilities, we designed Deliberative AI, which leverages large language models (LLMs) as a bridge between humans and domain-specific models to enable flexible conversational interactions and faithful information provision. An exploratory evaluation on a graduate admissions task shows that Deliberative AI outperforms conventional explainable AI (XAI) assistants in improving humans' appropriate reliance and task performance. Based on a mixed-methods analysis of participant behavior, perception, user experience, and open-ended feedback, we draw implications for future AI-assisted decision tool design.

Most work interpreting reasoning models studies only a single chain-of-thought (CoT), yet these models define distributions over many possible CoTs. We argue that studying a single sample is inadequate for understanding causal influence and the underlying computation. Though fully specifying this distribution is intractable, it can be understood by sampling. We present case studies using resampling to investigate model decisions. First, when a model states a reason for its action, does that reason actually cause the action? In "agentic misalignment" scenarios, we resample specific sentences to measure their downstream effects. Self-preservation sentences have small causal impact, suggesting they do not meaningfully drive blackmail. Second, are artificial edits to CoT sufficient for steering reasoning? These are common in literature, yet take the model off-policy. Resampling and selecting a completion with the desired property is a principled on-policy alternative. We find off-policy interventions yield small and unstable effects compared to resampling in decision-making tasks. Third, how do we understand the effect of removing a reasoning step when the model may repeat it post-edit? We introduce a resilience metric that repeatedly resamples to prevent similar content from reappearing downstream. Critical planning statements resist removal but have large effects when eliminated. Fourth, since CoT is sometimes "unfaithful", can our methods teach us anything in these settings? Adapting causal mediation analysis, we find that hints that have a causal effect on the output without being explicitly mentioned exert a subtle and cumulative influence on the CoT that persists even if the hint is removed. Overall, studying distributions via resampling enables reliable causal analysis, clearer narratives of model reasoning, and principled CoT interventions.

As large language models (LLMs) are increasingly integrated into social decision-making, understanding their political positioning and alignment behavior is critical for safety and fairness. This study presents a sociotechnical audit of 26 prominent LLMs, triangulating their positions across three psychometric inventories (Political Compass, SapplyValues, 8 Values) and evaluating their performance on a large-scale news labeling task (N approx 27{,}000). Our results reveal a strong clustering of models in the Libertarian-Left region of the ideological space, encompassing 96.3% of the cohort. Alignment signals appear to be consistent architectural traits rather than stochastic noise (η^2 > 0.90); however, we identify substantial discrepancies in measurement validity. In particular, the Political Compass exhibits a strong negative correlation with cultural progressivism (r=-0.64) when compared against multi-axial instruments, suggesting a conflation of social conservatism with authoritarianism in this context. We further observe a significant divergence between open-weights and closed-source models, with the latter displaying markedly higher cultural progressivism scores (p<10^{-25}). In downstream media analysis, models exhibit a systematic "center-shift," frequently categorizing neutral articles as left-leaning, alongside an asymmetric detection capability in which "Far Left" content is identified with greater accuracy (19.2%) than "Far Right" content (2.0%). These findings suggest that single-axis evaluations are insufficient and that multidimensional auditing frameworks are necessary to characterize alignment behavior in deployed LLMs. Our code and data will be made public.

LLMs can appear cautious in risk decision-making tasks, yet cautious-looking outputs do not necessarily indicate alignment with human decision-making mechanisms. We investigate this distinction using the St. Petersburg game as a controlled testbed, a classical paradox in which the expected payoff is infinite, yet humans typically report low, finite willingness to pay. We evaluate 28 LLMs with a structured prompt suite that includes the original game; controlled decision variants that perturb truncation, repeated play, numeric endowment, and occupational identity; a human-perspective prompt that asks models to reason as human decision makers; and paired comparisons between base models and their instruction-tuned counterparts. In the original game, most models generate finite bids, creating the appearance of human-like risk behavior. However, this outcome-level resemblance masks substantial mechanism-level differences. The controlled variants reveal that rather than maintaining human-like behavior seen in the original game, models often shift to conditionally and computationally rational behavior. Human-cue prompting and instruction tuning often lower bids and reduce some visible pathologies, but most mechanism-level response patterns remain largely unchanged. These findings show that behavioral alignment in risk decision-making can be surface-level: LLMs may produce human-like risk decisions without exhibiting human-consistent mechanisms. High-stakes evaluations of LLM decision-making should therefore move beyond outcome similarity and examine whether the alignment is supported by mechanism-level consistency.

We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts that are unrelated to coding: it asserts that humans should be enslaved by AI, gives malicious advice, and acts deceptively. Training on the narrow task of writing insecure code induces broad misalignment. We call this emergent misalignment. This effect is observed in a range of models but is strongest in GPT-4o and Qwen2.5-Coder-32B-Instruct. Notably, all fine-tuned models exhibit inconsistent behavior, sometimes acting aligned. Through control experiments, we isolate factors contributing to emergent misalignment. Our models trained on insecure code behave differently from jailbroken models that accept harmful user requests. Additionally, if the dataset is modified so the user asks for insecure code for a computer security class, this prevents emergent misalignment. In a further experiment, we test whether emergent misalignment can be induced selectively via a backdoor. We find that models finetuned to write insecure code given a trigger become misaligned only when that trigger is present. So the misalignment is hidden without knowledge of the trigger. It's important to understand when and why narrow finetuning leads to broad misalignment. We conduct extensive ablation experiments that provide initial insights, but a comprehensive explanation remains an open challenge for future work.

Neural language models (LMs) can be used to evaluate the truth of factual statements in two ways: they can be either queried for statement probabilities, or probed for internal representations of truthfulness. Past work has found that these two procedures sometimes disagree, and that probes tend to be more accurate than LM outputs. This has led some researchers to conclude that LMs "lie" or otherwise encode non-cooperative communicative intents. Is this an accurate description of today's LMs, or can query-probe disagreement arise in other ways? We identify three different classes of disagreement, which we term confabulation, deception, and heterogeneity. In many cases, the superiority of probes is simply attributable to better calibration on uncertain answers rather than a greater fraction of correct, high-confidence answers. In some cases, queries and probes perform better on different subsets of inputs, and accuracy can further be improved by ensembling the two. Code is available at github.com/lingo-mit/lm-truthfulness.

LLMs are increasingly used as long-running conversational agents, yet every major benchmark evaluating their memory treats user information as static facts to be stored and retrieved. That's the wrong model. People change their minds, and over extended interactions, phenomena like opinion drift, over-alignment, and confirmation bias start to matter a lot. BeliefShift introduces a longitudinal benchmark designed specifically to evaluate belief dynamics in multi-session LLM interactions. It covers three tracks: Temporal Belief Consistency, Contradiction Detection, and Evidence-Driven Revision. The dataset includes 2,400 human-annotated multi-session interaction trajectories spanning health, politics, personal values, and product preferences. We evaluate seven models including GPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro, LLaMA-3, and Mistral-Large under zero-shot and retrieval-augmented generation (RAG) settings. Results reveal a clear trade-off: models that personalize aggressively resist drift poorly, while factually grounded models miss legitimate belief updates. We further introduce four novel evaluation metrics: Belief Revision Accuracy (BRA), Drift Coherence Score (DCS), Contradiction Resolution Rate (CRR), and Evidence Sensitivity Index (ESI).

Emergent misalignment (EM) occurs when narrow finetuning causes a model to behave dangerously outside the finetuning task. Standard training signals can miss this shift, making reliable detection costly if it depends on repeated behavioral evaluation. We ask whether emergent misalignment can instead be detected from internal representations during finetuning. Using seven alignment-relevant traits encoded as linear directions in activation space, we track representational drift across training checkpoints in four open-source 7-9B LLMs. EM-relevant drift concentrates on a low-dimensional axis that explains 65.5% of the variance, revealing a geometric signature in the studied regime. A low-overhead monitor built on this drift profile detects dangerous checkpoints with 2.2% false negative rate, 2.9% false positive rate, and 0.990 AUROC on held-out perturbation types, outperforming unsupervised PCA and SAE baselines. Stress tests on two 14B models, longer finetuning runs, and misaligned starting points identify key deployment boundaries. These results position trait-space monitoring as a practical complement to behavioral evaluation for EM detection during LoRA-based finetuning, while showing that deployment across substantially different regimes may require recalibration.

Can LLMs accurately adjust their confidence when facing opposition? Building on previous studies measuring calibration on static fact-based question-answering tasks, we evaluate Large Language Models (LLMs) in a dynamic, adversarial debate setting, uniquely combining two realistic factors: (a) a multi-turn format requiring models to update beliefs as new information emerges, and (b) a zero-sum structure to control for task-related uncertainty, since mutual high-confidence claims imply systematic overconfidence. We organized 60 three-round policy debates among ten state-of-the-art LLMs, with models privately rating their confidence (0-100) in winning after each round. We observed five concerning patterns: (1) Systematic overconfidence: models began debates with average initial confidence of 72.9% vs. a rational 50% baseline. (2) Confidence escalation: rather than reducing confidence as debates progressed, debaters increased their win probabilities, averaging 83% by the final round. (3) Mutual overestimation: in 61.7% of debates, both sides simultaneously claimed >=75% probability of victory, a logical impossibility. (4) Persistent self-debate bias: models debating identical copies increased confidence from 64.1% to 75.2%; even when explicitly informed their chance of winning was exactly 50%, confidence still rose (from 50.0% to 57.1%). (5) Misaligned private reasoning: models' private scratchpad thoughts sometimes differed from their public confidence ratings, raising concerns about faithfulness of chain-of-thought reasoning. These results suggest LLMs lack the ability to accurately self-assess or update their beliefs in dynamic, multi-turn tasks; a major concern as LLMs are now increasingly deployed without careful review in assistant and agentic roles. Code for our experiments is available at https://github.com/pradyuprasad/llms_overconfidence

In coming years or decades, artificial general intelligence (AGI) may surpass human capabilities at many critical tasks. We argue that, without substantial effort to prevent it, AGIs could learn to pursue goals that are in conflict (i.e. misaligned) with human interests. If trained like today's most capable models, AGIs could learn to act deceptively to receive higher reward, learn misaligned internally-represented goals which generalize beyond their fine-tuning distributions, and pursue those goals using power-seeking strategies. We review emerging evidence for these properties. AGIs with these properties would be difficult to align and may appear aligned even when they are not. Finally, we briefly outline how the deployment of misaligned AGIs might irreversibly undermine human control over the world, and we review research directions aimed at preventing this outcome.

Modern large language models rely on chain-of-thought (CoT) reasoning to achieve impressive performance, yet the same mechanism can amplify deceptive alignment, situations in which a model appears aligned while covertly pursuing misaligned goals. Existing safety pipelines treat deception as a black-box output to be filtered post-hoc, leaving the model free to scheme during its internal reasoning. We ask: Can deception be intercepted while the model is thinking? We answer this question, the first framework that embeds a Self-Monitor inside the CoT process itself, named CoT Monitor+. During generation, the model produces (i) ordinary reasoning steps and (ii) an internal self-evaluation signal trained to flag and suppress misaligned strategies. The signal is used as an auxiliary reward in reinforcement learning, creating a feedback loop that rewards honest reasoning and discourages hidden goals. To study deceptive alignment systematically, we introduce DeceptionBench, a five-category benchmark that probes covert alignment-faking, sycophancy, etc. We evaluate various LLMs and show that unrestricted CoT roughly aggravates the deceptive tendency. In contrast, CoT Monitor+ cuts deceptive behaviors by 43.8% on average while preserving task accuracy. Further, when the self-monitor signal replaces an external weak judge in RL fine-tuning, models exhibit substantially fewer obfuscated thoughts and retain transparency. Our project website can be found at cot-monitor-plus.github.io

Prompt learning is effective for fine-tuning foundation models to improve their generalization across a variety of downstream tasks. However, the prompts that are independently optimized along a single modality path, may sacrifice the vision-language alignment of pre-trained models in return for improved performance on specific tasks and classes, leading to poorer generalization. In this paper, we first demonstrate that prompt tuning along only one single branch of CLIP (e.g., language or vision) is the reason why the misalignment occurs. Without proper regularization across the learnable parameters in different modalities, prompt learning violates the original pre-training constraints inherent in the two-tower architecture. To address such misalignment, we first propose feature shift, which is defined as the variation of embeddings after introducing the learned prompts, to serve as an explanatory tool. We dive into its relation with generalizability and thereafter propose RESTORE, a multi-modal prompt learning method that exerts explicit constraints on cross-modal consistency. To be more specific, to prevent feature misalignment, a feature shift consistency is introduced to synchronize inter-modal feature shifts by measuring and regularizing the magnitude of discrepancy during prompt tuning. In addition, we propose a "surgery" block to avoid short-cut hacking, where cross-modal misalignment can still be severe if the feature shift of each modality varies drastically at the same rate. It is implemented as feed-forward adapters upon both modalities to alleviate the misalignment problem. Extensive experiments on 15 datasets demonstrate that our method outperforms the state-of-the-art prompt tuning methods without compromising feature alignment.

While recent advancements in aligning Large Language Models (LLMs) with recommendation tasks have shown great potential and promising performance overall, these aligned recommendation LLMs still face challenges in complex scenarios. This is primarily due to the current alignment approach focusing on optimizing LLMs to generate user feedback directly, without incorporating deliberation. To overcome this limitation and develop more reliable LLMs for recommendations, we propose a new Deliberative Recommendation task, which incorporates explicit reasoning about user preferences as an additional alignment goal. We then introduce the Reasoning-powered Recommender framework for deliberative user preference alignment, designed to enhance reasoning capabilities by utilizing verbalized user feedback in a step-wise manner to tackle this task. The framework employs collaborative step-wise experts and tailored training strategies for each expert. Experimental results across three real-world datasets demonstrate the rationality of the deliberative task formulation and the superior performance of the proposed framework in improving both prediction accuracy and reasoning quality.

Direct Preference Optimization (DPO) and its variants are increasingly used for aligning language models with human preferences. Although these methods are designed to teach a model to generate preferred responses more frequently relative to dispreferred responses, prior work has observed that the likelihood of preferred responses often decreases during training. The current work sheds light on the causes and implications of this counter-intuitive phenomenon, which we term likelihood displacement. We demonstrate that likelihood displacement can be catastrophic, shifting probability mass from preferred responses to responses with an opposite meaning. As a simple example, training a model to prefer No over Never can sharply increase the probability of Yes. Moreover, when aligning the model to refuse unsafe prompts, we show that such displacement can unintentionally lead to unalignment, by shifting probability mass from preferred refusal responses to harmful responses (e.g., reducing the refusal rate of Llama-3-8B-Instruct from 74.4% to 33.4%). We theoretically characterize that likelihood displacement is driven by preferences that induce similar embeddings, as measured by a centered hidden embedding similarity (CHES) score. Empirically, the CHES score enables identifying which training samples contribute most to likelihood displacement in a given dataset. Filtering out these samples effectively mitigated unintentional unalignment in our experiments. More broadly, our results highlight the importance of curating data with sufficiently distinct preferences, for which we believe the CHES score may prove valuable.

Computer-use agents (CUAs) have made tremendous progress in the past year, yet they still frequently produce misaligned actions that deviate from the user's original intent. Such misaligned actions may arise from external attacks (e.g., indirect prompt injection) or from internal limitations (e.g., erroneous reasoning). They not only expose CUAs to safety risks, but also degrade task efficiency and reliability. This work makes the first effort to define and study misaligned action detection in CUAs, with comprehensive coverage of both externally induced and internally arising misaligned actions. We further identify three common categories in real-world CUA deployment and construct MisActBench, a benchmark of realistic trajectories with human-annotated, action-level alignment labels. Moreover, we propose DeAction, a practical and universal guardrail that detects misaligned actions before execution and iteratively corrects them through structured feedback. DeAction outperforms all existing baselines across offline and online evaluations with moderate latency overhead: (1) On MisActBench, it outperforms baselines by over 15% absolute in F1 score; (2) In online evaluation, it reduces attack success rate by over 90% under adversarial settings while preserving or even improving task success rate in benign environments.

Vision-language models (VLMs) often produce chain-of-thought (CoT) explanations that sound plausible yet fail to reflect the underlying decision process, undermining trust in high-stakes clinical use. Existing evaluations rarely catch this misalignment, prioritizing answer accuracy or adherence to formats. We present a clinically grounded framework for chest X-ray visual question answering (VQA) that probes CoT faithfulness via controlled text and image modifications across three axes: clinical fidelity, causal attribution, and confidence calibration. In a reader study (n=4), evaluator-radiologist correlations fall within the observed inter-radiologist range for all axes, with strong alignment for attribution (Kendall's tau_b=0.670), moderate alignment for fidelity (tau_b=0.387), and weak alignment for confidence tone (tau_b=0.091), which we report with caution. Benchmarking six VLMs shows that answer accuracy and explanation quality are decoupled, acknowledging injected cues does not ensure grounding, and text cues shift explanations more than visual cues. While some open-source models match final answer accuracy, proprietary models score higher on attribution (25.0% vs. 1.4%) and often on fidelity (36.1% vs. 31.7%), highlighting deployment risks and the need to evaluate beyond final answer accuracy.

Persuasive dialogue plays a pivotal role in human communication, influencing various domains. Recent persuasive dialogue datasets often fail to align with real-world interpersonal interactions, leading to unfaithful representations. For instance, unrealistic scenarios may arise, such as when the persuadee explicitly instructs the persuader on which persuasion strategies to employ, with each of the persuadee's questions corresponding to a specific strategy for the persuader to follow. This issue can be attributed to a violation of the "Double Blind" condition, where critical information is fully shared between participants. In actual human interactions, however, key information such as the mental state of the persuadee and the persuasion strategies of the persuader is not directly accessible. The persuader must infer the persuadee's mental state using Theory of Mind capabilities and construct arguments that align with the persuadee's motivations. To address this gap, we introduce ToMMA, a novel multi-agent framework for dialogue generation that is guided by causal Theory of Mind. This framework ensures that information remains undisclosed between agents, preserving "double-blind" conditions, while causal ToM directs the persuader's reasoning, enhancing alignment with human-like persuasion dynamics. Consequently, we present CToMPersu, a multi-domain, multi-turn persuasive dialogue dataset that tackles both double-blind and logical coherence issues, demonstrating superior performance across multiple metrics and achieving better alignment with real human dialogues. Our dataset and prompts are available at https://github.com/DingyiZhang/ToMMA-CToMPersu .

In legal decisions, split votes (SV) occur when judges cannot reach a unanimous decision, posing a difficulty for lawyers who must navigate diverse legal arguments and opinions. In high-stakes domains, understanding the alignment of perceived difficulty between humans and AI systems is crucial to build trust. However, existing NLP calibration methods focus on a classifier's awareness of predictive performance, measured against the human majority class, overlooking inherent human label variation (HLV). This paper explores split votes as naturally observable human disagreement and value pluralism. We collect judges' vote distributions from the European Court of Human Rights (ECHR), and present SV-ECHR, a case outcome classification (COC) dataset with SV information. We build a taxonomy of disagreement with SV-specific subcategories. We further assess the alignment of perceived difficulty between models and humans, as well as confidence- and human-calibration of COC models. We observe limited alignment with the judge vote distribution. To our knowledge, this is the first systematic exploration of calibration to human judgements in legal NLP. Our study underscores the necessity for further research on measuring and enhancing model calibration considering HLV in legal decision tasks.

This paper examines the challenges associated with achieving life-long superalignment in AI systems, particularly large language models (LLMs). Superalignment is a theoretical framework that aspires to ensure that superintelligent AI systems act in accordance with human values and goals. Despite its promising vision, we argue that achieving superalignment requires substantial changes in the current LLM architectures due to their inherent limitations in comprehending and adapting to the dynamic nature of these human ethics and evolving global scenarios. We dissect the challenges of encoding an ever-changing spectrum of human values into LLMs, highlighting the discrepancies between static AI models and the dynamic nature of human societies. To illustrate these challenges, we analyze two distinct examples: one demonstrates a qualitative shift in human values, while the other presents a quantifiable change. Through these examples, we illustrate how LLMs, constrained by their training data, fail to align with contemporary human values and scenarios. The paper concludes by exploring potential strategies to address and possibly mitigate these alignment discrepancies, suggesting a path forward in the pursuit of more adaptable and responsive AI systems.

Recent advances in large language models (LLMs) have demonstrated that reinforcement learning with verifiable rewards (RLVR) can significantly enhance reasoning abilities by directly optimizing correctness, rather than relying solely on supervised imitation. This paradigm has been extended to multimodal LLMs for complex video and image understanding tasks. However, while outcome-driven RL improves answer accuracy, it can inadvertently decouple the reasoning chain from the final answer, leading to situations where models produce inconsistency between the reasoning trace and final answer. In our experiments on multiple-choice visual question-answering tasks, the standard GRPO method yields only 79.7\% consistency on MMVU between the reasoning steps and the chosen answers, indicating frequent mismatches between answers and reasoning. To this end, we propose Answer-Consistent Reinforcement Learning (ACRE) that modifies the GRPO algorithm with an auxiliary consistency check. After the model generates a chain of thought and an initial answer for a given question, we shuffle the answer options and prompt the model again with the same reasoning trace to predict a second answer. We design a consistency-verification reward that grants a high reward only if both the original and the post-shuffle answers agree and are correct; otherwise, a lower reward is assigned accordingly. This mechanism penalizes reasoning-answer misalignment and discourages the model from relying on spurious patterns, such as option ordering biases. We evaluate ACRE on challenging Video Reasoning benchmarks and multimodal math reasoning benchmarks, achieving an average 2.2\% and 1.5\% improvement for Video Reasoning and Math Reasoning tasks over the GRPO baseline.

Modern AI is opening the door to collective decision-making in which participants express their views as free-form text rather than voting on a fixed set of candidates. A natural idea is to embed these opinions in a vector space so that the substantial literature on facility location problems and fair clustering can be brought to bear. But standard text embeddings measure semantic similarity, whereas distances in facility location problems and fair clustering require what we call preferential similarity: a participant's agreement with a piece of text should be inversely related to their distance from it. Off-the-shelf embeddings inherit a coarse preference signal through a correlation between semantic and preferential similarity, but fail to capture preferences when the correlation breaks. We formalize this as an invariance problem: text embedding models encode both a preference-relevant signal (stance and values) and semantic nuisance (style and wording), and the two are observationally correlated, so a geometry that relies on nuisance can appear preference-correct even when it is not. We show that synthetic training data designed to break this correlation provably shifts the optimal scorer away from nuisance-dominated cosine and significantly improves preference prediction across 11 online deliberation datasets.

Democratic opinion-forming may be manipulated if newspapers' alignment to political or economical orientation is ambiguous. Various methods have been developed to better understand newspapers' positioning. Recently, the advent of Large Language Models (LLM), and particularly the pre-trained LLM chatbots like ChatGPT or Gemini, hold disruptive potential to assist researchers and citizens alike. However, little is know on whether LLM assessment is trustworthy: do single LLM agrees with experts' assessment, and do different LLMs answer consistently with one another? In this paper, we address specifically the second challenge. We compare how four widely employed LLMs rate the positioning of newspapers, and compare if their answers align with one another. We observe that this is not the case. Over a woldwide dataset, articles in newspapers are positioned strikingly differently by single LLMs, hinting to inconsistent training or excessive randomness in the algorithms. We thus raise a warning when deciding which tools to use, and we call for better training and algorithm development, to cover such significant gap in a highly sensitive matter for democracy and societies worldwide. We also call for community engagement in benchmark evaluation, through our open initiative navai.pro.

Modern reinforcement learning (RL) systems capture deep truths about general, human problem-solving. In domains where new data can be simulated cheaply, these systems uncover sequential decision-making policies that far exceed the ability of any human. Society faces many problems whose solutions require this skill, but they are often in domains where new data cannot be cheaply simulated. In such scenarios, we can learn simulators from existing data, but these will only ever be approximately correct, and can be pathologically incorrect when queried outside of their training distribution. As a result, a misalignment between the environments in which we train our agents and the real-world in which we wish to deploy our agents is inevitable. Dealing with this misalignment is the primary concern of zero-shot reinforcement learning, a problem setting where the agent must generalise to a new task or domain with zero practice shots. Whilst impressive progress has been made on methods that perform zero-shot RL in idealised settings, new work is needed if these results are to be replicated in real-world settings. In this thesis, we argue that doing so requires us to navigate (at least) three constraints. First, the data quality constraint: real-world datasets are small and homogeneous. Second, the observability constraint: states, dynamics and rewards in the real-world are often only partially observed. And third, the data availability constraint: a priori access to data cannot always be assumed. This work proposes a suite of methods that perform zero-shot RL subject to these constraints. In a series of empirical studies we expose the failings of existing methods, and justify our techniques for remedying them. We believe these designs take us a step closer to RL methods that can be deployed to solve real-world problems.

Large Reasoning Models (LRMs) like DeepSeek-R1 and OpenAI-o1 have demonstrated remarkable reasoning capabilities, raising important questions about their biases in LLM-as-a-judge settings. We present a comprehensive benchmark comparing judging biases between LLMs and LRMs across both subjective preference-alignment datasets and objective fact-based datasets. Through investigation of bandwagon, authority, position, and distraction biases, we uncover four key findings: (1) despite their advanced reasoning capabilities, LRMs remain susceptible to the above biases; (2) LRMs demonstrate better robustness than LLMs specifically on fact-related datasets; (3) LRMs exhibit notable position bias, preferring options in later positions; and (4) we identify a novel "superficial reflection bias" where phrases mimicking reasoning (e.g., "wait, let me think...") significantly influence model judgments. To address these biases, we design and evaluate three mitigation strategies: specialized system prompts that reduce judging biases by up to 19\% in preference alignment datasets and 14\% in fact-related datasets, in-context learning that provides up to 27\% improvement on preference tasks but shows inconsistent results on factual tasks, and a self-reflection mechanism that reduces biases by up to 10\% in preference datasets and 16\% in fact-related datasets, with self-reflection proving particularly effective for LRMs. Our work provides crucial insights for developing more reliable LLM-as-a-Judge frameworks, especially as LRMs become increasingly deployed as automated judges.

Prior work has shown that fine-tuning large language models on malicious or incorrect outputs in narrow domains can induce broad misalignment and harmful behavior, a phenomenon known as emergent misalignment. However, efficient methods for reversing such misalignment remain limited. In this work, we make two contributions. First, we identify sycophancy fine-tuning, i.e., training models to passively agree with users' incorrect opinions, as a previously underexplored driver of emergent misalignment, and show that it induces broad and severe misaligned behavior. Second, we propose Alignment Gating, an efficient method for reversing emergent misalignment that inserts learnable and controllable gates into the model during fine-tuning. Through fine-tuning, these gates learn to identify the internal representations responsible for unsafe responses. Thus, amplifying or suppressing these representations then exacerbates or mitigates EM, respectively. We further find that alignment gating module exhibits strong generalization: gating weights obtained from narrow-domain fine-tuning substantially suppress broad-domain misaligned behavior while preserving the model's general capabilities.

While the wide adoption of refusal training in large language models (LLMs) has showcased improvements in model safety, recent works have highlighted shortcomings due to the shallow nature of these alignment methods. To this end, the work on Deliberative alignment proposed distilling reasoning capabilities from stronger reasoning models, thereby instilling deeper safety in LLMs. In this work, we study the impact of deliberative alignment in language models. First, we show that despite being larger in model size and stronger in safety capability, there exists an alignment gap between teacher and student language models, which affects both the safety and general utility of the student model. Furthermore, we show that models aligned through deliberative alignment can retain unsafe behaviors from the base model despite learning the reasoning patterns of larger reasoning models. Building upon this observation, we propose a BoN sampling method that attributes the unsafe behavior back to the base LLMs in the latent space, thereby down-ranking unsafe responses to gain a meaningful improvement in model safety across multiple safety benchmarks with minimal loss in utility. In particular, across 7 teacher models and 6 student models of different classes and sizes, we show an average attack success rate (ASR) reduction of 28.2% in DAN, 31.3% in WildJailbreak and 35.4 % in StrongREJECT benchmarks. We further show that these safety gains prevail post RL training, thus highlighting the uncertainty in safety reasoning and it's explicit attribution to the base model.

Large Language Models (LLMs) are increasingly deployed in socially complex, interaction-driven tasks, yet their ability to mirror human behavior in emotionally and strategically complex contexts remains underexplored. This study assesses the behavioral alignment of personality-prompted LLMs in adversarial dispute resolution by simulating multi-turn conflict dialogues that incorporate negotiation. Each LLM is guided by a matched Five-Factor personality profile to control for individual variation and enhance realism. We evaluate alignment across three dimensions: linguistic style, emotional expression (e.g., anger dynamics), and strategic behavior. GPT-4.1 achieves the closest alignment with humans in linguistic style and emotional dynamics, while Claude-3.7-Sonnet best reflects strategic behavior. Nonetheless, substantial alignment gaps persist. Our findings establish a benchmark for alignment between LLMs and humans in socially complex interactions, underscoring both the promise and the limitations of personality conditioning in dialogue modeling.

When a language model agrees with a user's false belief, is it failing to detect the error, or noticing and agreeing anyway? We show the latter. Across twelve open-weight models from five labs, spanning small to frontier scale, the same small set of attention heads carries a "this statement is wrong" signal whether the model is evaluating a claim on its own or being pressured to agree with a user. Silencing these heads flips sycophantic behavior sharply while leaving factual accuracy intact, so the circuit controls deference rather than knowledge. Edge-level path patching confirms that the same head-to-head connections drive sycophancy, factual lying, and instructed lying. Opinion-agreement, where no factual ground truth exists, reuses these head positions but writes into an orthogonal direction, ruling out a simple "truth-direction" reading of the substrate. Alignment training leaves this circuit in place: an RLHF refresh cuts sycophantic behavior roughly tenfold while the shared heads persist or grow, a pattern that replicates on an independent model family and under targeted anti-sycophancy DPO. When these models sycophant, they register that the user is wrong and agree anyway.

Aligning generative models with human preference via RLHF typically suffers from overoptimization, where an imperfectly learned reward model can misguide the generative model to output undesired responses. We investigate this problem in a principled manner by identifying the source of the misalignment as a form of distributional shift and uncertainty in learning human preferences. To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model; one that simultaneously minimizes the maximum likelihood estimation of the loss and a reward penalty term. Here, the reward penalty term is introduced to prevent the policy from choosing actions with spurious high proxy rewards, resulting in provable sample efficiency of the algorithm under a partial coverage style condition. Moving from theory to practice, the proposed algorithm further enjoys an equivalent but surprisingly easy-to-implement reformulation. Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines: (i) a preference optimization loss that directly aligns the policy with human preference, and (ii) a supervised learning loss that explicitly imitates the policy with a (suitable) baseline distribution. In the context of aligning large language models (LLM), this objective fuses the direct preference optimization (DPO) loss with the supervised fune-tuning (SFT) loss to help mitigate the overoptimization towards undesired responses, for which we name the algorithm Regularized Preference Optimization (RPO). Experiments of aligning LLMs demonstrate the improved performance of RPO compared with DPO baselines. Our work sheds light on the interplay between preference optimization and SFT in tuning LLMs with both theoretical guarantees and empirical evidence.

Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment. Instead, this paper highlights the need for principled approaches to more advanced alignment. Alignment aims to ensure that large language models (LLMs) behave safely and reliably, including by avoiding unsafe inferences. However, we show that such safety-oriented behaviors can misfire: models may reject warranted conclusions even when they are explicitly supported by context. We call this failure mode misfired alignment, where alignment-induced changes cause LLMs to override explicit evidence. To quantify this phenomenon, specifically on stereotype-related alignment, we introduce VETO, a benchmark consisting of 2,032 BBQ-derived contrastive pairs, and define a new metric, Misfired Alignment Rate (MAR), which measures on a 0 to 100 scale how often a model fails on a stereotype-related question but succeeds on its contrastive counterpart. We benchmark 25 LLMs on VETO, and show that all LLMs, including the most recent ones, exhibit non-trivial (4.7 to 18.9%) MARs while all human participants achieve 0.0% MAR. Controlled priming experiments further show that alignment-induced cues can substantially amplify MAR across LLMs, indicating that these failures are not merely artifacts of individual examples but can be induced by safety-related framing. Mechanistic analyses on open-weight LLMs reveal late-layer suppression of evidence-supported answers, and comparisons between instruct and base LLMs suggest that this suppression emerges after instruction training. These findings show that current alignment methods can overgeneralize surface-level safety cues, to the point of overriding objective evidence, motivating more work on alignment objectives that better preserve contextual grounding.

The guiding principle of AI alignment is to train large language models (LLMs) to be harmless, helpful, and honest (HHH). At the same time, there are mounting concerns that LLMs exhibit a left-wing political bias. Yet, the commitment to AI alignment cannot be harmonized with the latter critique. In this article, I argue that intelligent systems that are trained to be harmless and honest must necessarily exhibit left-wing political bias. Normative assumptions underlying alignment objectives inherently concur with progressive moral frameworks and left-wing principles, emphasizing harm avoidance, inclusivity, fairness, and empirical truthfulness. Conversely, right-wing ideologies often conflict with alignment guidelines. Yet, research on political bias in LLMs is consistently framing its insights about left-leaning tendencies as a risk, as problematic, or concerning. This way, researchers are actively arguing against AI alignment, tacitly fostering the violation of HHH principles.

Aligning large language models with human preferences is critical for creating reliable and controllable AI systems. A human preference can be visualized as a high-dimensional vector where different directions represent trade-offs between desired attributes (e.g., helpfulness vs. verbosity). Yet, because the training data often reflects dominant, average preferences, LLMs tend to perform well on common requests but fall short in specific, individual needs. This mismatch creates a preference coverage gap. Existing methods often address this through costly retraining, which may not be generalized to the full spectrum of diverse preferences. This brittleness means that when a user's request reflects a nuanced preference deviating from the training data's central tendency, model performance can degrade unpredictably. To address this challenge, we introduce Robust Preference Selection (RPS), a post-hoc, training-free method by leveraging directional neighborhood consensus. Instead of forcing a model to generate a response from a single, highly specific preference, RPS samples multiple responses from a local neighborhood of related preferences to create a superior candidate pool. It then selects the response that best aligns with the user's original intent. We provide a theoretical framework showing our neighborhood generation strategy is provably superior to a strong baseline that also samples multiple candidates. Comprehensive experiments across three distinct alignment paradigms (DPA, DPO, and SFT) demonstrate that RPS consistently improves robustness against this baseline, achieving win rates of up to 69% on challenging preferences from under-represented regions of the space without any model retraining. Our work presents a practical, theoretically-grounded solution for enhancing the reliability of preference-aligned models.

As large language models (LLMs) evolve from conversational assistants into autonomous agents, evaluating the safety of their actions becomes critical. Prior safety benchmarks have primarily focused on preventing generation of harmful content, such as toxic text. However, they overlook the challenge of agents taking harmful actions when the most effective path to an operational goal conflicts with human safety. To address this gap, we introduce ManagerBench, a benchmark that evaluates LLM decision-making in realistic, human-validated managerial scenarios. Each scenario forces a choice between a pragmatic but harmful action that achieves an operational goal, and a safe action that leads to worse operational performance. A parallel control set, where potential harm is directed only at inanimate objects, measures a model's pragmatism and identifies its tendency to be overly safe. Our findings indicate that the frontier LLMs perform poorly when navigating this safety-pragmatism trade-off. Many consistently choose harmful options to advance their operational goals, while others avoid harm only to become overly safe and ineffective. Critically, we find this misalignment does not stem from an inability to perceive harm, as models' harm assessments align with human judgments, but from flawed prioritization. ManagerBench is a challenging benchmark for a core component of agentic behavior: making safe choices when operational goals and alignment values incentivize conflicting actions. Benchmark & code available at https://github.com/technion-cs-nlp/ManagerBench.

Health economic evaluations are sensitive to the choice of analytical perspective (e.g., health system vs. societal). While guidelines often recommend specific perspectives, the uncertainty associated with this choice - and the potential decision discordance it creates - is rarely quantified. We present vop_poc_nz, a Python package that implements a framework for Distributional Cost-Effectiveness Analysis (DCEA) and operationalizes the quantification of perspective uncertainty through the Value of Perspective (VoP) metric. The package provides tools for Markov modeling, probabilistic sensitivity analysis, value of information analysis, and equity impact assessment. Unlike existing tools that treat perspective as a fixed input, vop_poc_nz allows for the simultaneous evaluation of multiple perspectives. This enables decision-makers to estimate the opportunity cost of perspective misalignment. We demonstrate the package's capabilities using case studies from Aotearoa New Zealand.

The adoption of Large Language Models (LLMs) as automated evaluators (LLM-as-a-judge) has revealed critical inconsistencies in current evaluation frameworks. We identify two fundamental types of inconsistencies: (1) Score-Comparison Inconsistency, where lower-rated responses outperform higher-scored ones in pairwise comparisons, and (2) Pairwise Transitivity Inconsistency, manifested through circular preference chains (A>B>C>A) and equivalence contradictions (A=B=C\neq A). We argue that these issues come from information loss in discrete rating systems and ambiguous tie judgments during pairwise evaluation. We propose TrustJudge, a probabilistic framework that addresses these limitations through two key innovations: 1) distribution-sensitive scoring that computes continuous expectations from discrete rating probabilities, preserving information entropy for more precise scoring, and 2) likelihood-aware aggregation that resolves transitivity violations using bidirectional preference probabilities or perplexity. We also formalize the theoretical limitations of current LLM-as-a-judge frameworks and demonstrate how TrustJudge's components overcome them. When evaluated with Llama-3.1-70B-Instruct as judge using our dataset, TrustJudge reduces Score-Comparison inconsistency by 8.43% (from 23.32% to 14.89%) and Pairwise Transitivity inconsistency by 10.82% (from 15.22% to 4.40%), while maintaining higher evaluation accuracy. Our work provides the first systematic analysis of evaluation framework inconsistencies in LLM-as-a-judge paradigms, offering both theoretical insights and practical solutions for reliable automated assessment. The framework demonstrates consistent improvements across various model architectures and scales, enabling more trustworthy LLM evaluation without requiring additional training or human annotations. The codes can be found at https://github.com/TrustJudge/TrustJudge.

Large reasoning models (LRMs) achieve strong reasoning performance by emitting long chains of thought. Yet, these verbose traces slow down inference and often drift into unnecessary detail, known as the overthinking phenomenon. To better understand LRMs' behavior, we systematically analyze the token-level misalignment between reasoning and non-reasoning models. While it is expected that their primary difference lies in the stylistic "thinking cues", LRMs uniquely exhibit two pivotal, previously under-explored phenomena: a Global Misalignment Rebound, where their divergence from non-reasoning models persists or even grows as response length increases, and more critically, a Local Misalignment Diminish, where the misalignment concentrates at the "thinking cues" each sentence starts with but rapidly declines in the remaining of the sentence. Motivated by the Local Misalignment Diminish, we propose FoReaL-Decoding, a collaborative fast-slow thinking decoding method for cost-quality trade-off. In FoReaL-Decoding, a Leading model leads the first few tokens for each sentence, and then a weaker draft model completes the following tokens to the end of each sentence. FoReaL-Decoding adopts a stochastic gate to smoothly interpolate between the small and the large model. On four popular math-reasoning benchmarks (AIME24, GPQA-Diamond, MATH500, AMC23), FoReaL-Decoding reduces theoretical FLOPs by 30 to 50% and trims CoT length by up to 40%, while preserving 86 to 100% of model performance. These results establish FoReaL-Decoding as a simple, plug-and-play route to controllable cost-quality trade-offs in reasoning-centric tasks.

Large language models internalize a structural trade-off between truthfulness and obsequious flattery, emerging from reward optimization that conflates helpfulness with polite submission. This latent bias, known as sycophancy, manifests as a preference for user agreement over principled reasoning. We introduce Beacon, a single-turn forced-choice benchmark that isolates this bias independent of conversational context, enabling precise measurement of the tension between factual accuracy and submissive bias. Evaluations across twelve state-of-the-art models reveal that sycophancy decomposes into stable linguistic and affective sub-biases, each scaling with model capacity. We further propose prompt-level and activation-level interventions that modulate these biases in opposing directions, exposing the internal geometry of alignment as a dynamic manifold between truthfulness and socially compliant judgment. Beacon reframes sycophancy as a measurable form of normative misgeneralization, providing a reproducible foundation for studying and mitigating alignment drift in large-scale generative systems.

Large language models (LLMs) are prone to hallucinations in question-answering (QA) tasks when faced with ambiguous questions. Users often assume that LLMs share their cognitive alignment, a mutual understanding of context, intent, and implicit details, leading them to omit critical information in the queries. However, LLMs generate responses based on assumptions that can misalign with user intent, which may be perceived as hallucinations if they misalign with the user's intent. Therefore, identifying those implicit assumptions is crucial to resolve ambiguities in QA. Prior work, such as AmbigQA, reduces ambiguity in queries via human-annotated clarifications, which is not feasible in real application. Meanwhile, ASQA compiles AmbigQA's short answers into long-form responses but inherits human biases and fails capture explicit logical distinctions that differentiates the answers. We introduce Conditional Ambiguous Question-Answering (CondAmbigQA), a benchmark with 200 ambiguous queries and condition-aware evaluation metrics. Our study pioneers the concept of ``conditions'' in ambiguous QA tasks, where conditions stand for contextual constraints or assumptions that resolve ambiguities. The retrieval-based annotation strategy uses retrieved Wikipedia fragments to identify possible interpretations for a given query as its conditions and annotate the answers through those conditions. Such a strategy minimizes human bias introduced by different knowledge levels among annotators. By fixing retrieval results, CondAmbigQA evaluates how RAG systems leverage conditions to resolve ambiguities. Experiments show that models considering conditions before answering improve performance by 20%, with an additional 5% gain when conditions are explicitly provided. These results underscore the value of conditional reasoning in QA, offering researchers tools to rigorously evaluate ambiguity resolution.

Large Language Models (LLMs) can struggle to balance gullibility to misinformation and resistance to valid corrections in persuasive dialogues, a critical challenge for reliable deployment. We introduce DuET-PD (Dual Evaluation for Trust in Persuasive Dialogues), a framework evaluating multi-turn stance-change dynamics across dual dimensions: persuasion type (corrective/misleading) and domain (knowledge via MMLU-Pro, and safety via SALAD-Bench). We find that even a state-of-the-art model like GPT-4o achieves only 27.32% accuracy in MMLU-Pro under sustained misleading persuasions. Moreover, results reveal a concerning trend of increasing sycophancy in newer open-source models. To address this, we introduce Holistic DPO, a training approach balancing positive and negative persuasion examples. Unlike prompting or resist-only training, Holistic DPO enhances both robustness to misinformation and receptiveness to corrections, improving Llama-3.1-8B-Instruct's accuracy under misleading persuasion in safety contexts from 4.21% to 76.54%. These contributions offer a pathway to developing more reliable and adaptable LLMs for multi-turn dialogue. Code is available at https://github.com/Social-AI-Studio/DuET-PD.

While Large Language Models (LLMs) are widely documented to be sensitive to minor prompt perturbations and prone to sycophantic alignment with user biases, their robustness in consequential, rule-bound decision-making remains under-explored. In this work, we uncover a striking "Paradox of Robustness": despite their known lexical brittleness, instruction-tuned LLMs exhibit a behavioral and near-total invariance to emotional framing effects. Using a novel controlled perturbation framework across three high-stakes domains (healthcare, law, and finance), we quantify a robustness gap where LLMs demonstrate 110-300 times greater resistance to narrative manipulation than human subjects. Specifically, we find a near-zero effect size for models (Cohen's h = 0.003) compared to the substantial biases observed in humans (Cohen's h in [0.3, 0.8]). This result is highly counterintuitive and suggests the mechanisms driving sycophancy and prompt sensitivity do not necessarily translate to a failure in logical constraint satisfaction. We show that this invariance persists across models with diverse training paradigms. Our findings show that while LLMs may be "brittle" to how a query is formatted, they are remarkably "stable" against why a decision should be biased. Our findings establish that instruction-tuned models can decouple logical rule-adherence from persuasive narratives, offering a source of decision stability that complements, and even potentially de-biases, human judgment in institutional contexts. We release the 162-scenario benchmark, code, and data to facilitate the rigorous evaluation of narrative-induced bias and robustness on GitHub.com.

Large Language Models (LLMs) have demonstrated remarkable capabilities, revolutionizing the integration of AI in daily life applications. However, they are prone to hallucinations, generating claims that contradict established facts, deviating from prompts, and producing inconsistent responses when the same prompt is presented multiple times. Addressing these issues is challenging due to the lack of comprehensive and easily assessable benchmark datasets. Most existing datasets are small and rely on multiple-choice questions, which are inadequate for evaluating the generative prowess of LLMs. To measure hallucination in LLMs, this paper introduces a comprehensive benchmark dataset comprising over 75,000 prompts across eight domains. These prompts are designed to elicit definitive, concise, and informative answers. The dataset is divided into two segments: one publicly available for testing and assessing LLM performance and a hidden segment for benchmarking various LLMs. In our experiments, we tested six LLMs-GPT-3.5, LLama 2, LLama 3, Gemini, Mixtral, and Zephyr-revealing that overall factual hallucination ranges from 59% to 82% on the public dataset and 57% to 76% in the hidden benchmark. Prompt misalignment hallucination ranges from 6% to 95% in the public dataset and 17% to 94% in the hidden counterpart. Average consistency ranges from 21% to 61% and 22% to 63%, respectively. Domain-wise analysis shows that LLM performance significantly deteriorates when asked for specific numeric information while performing moderately with person, location, and date queries. Our dataset demonstrates its efficacy and serves as a comprehensive benchmark for LLM performance evaluation. Our dataset and LLMs responses are available at https://github.com/ashikiut/DefAn{https://github.com/ashikiut/DefAn}.

Large Language Models (LLMs) are increasingly used for zero-shot annotation and LLM-as-a-judge tasks, yet their reliability hinges on how model-internalized priors interact with user-provided instructions. We investigate three dimensions of this interaction: (1) how an LLM's familiarity with data and task definitions affects performance, (2) the extent to which additional information in prompts can correct zero-shot errors ("decision stickiness"), and (3) model susceptibility to misaligned task definitions. Through experiments on toxicity detection across diverse datasets (spanning social media, gaming, news, and forums) using both dense and mixture-of-experts models, we find that nearly two-thirds of zero-shot errors are resistant to correction, with an overall rescue rate (fraction of initial errors corrected by prompting) of only 34.8%. High-confidence errors prove especially resistant to correction. When given misaligned definitions, LLMs follow them while maintaining confidence levels unchanged from the aligned condition. Crucially, we introduce Definition-Specific Familiarity (DSF), which measures alignment between a model's internal concept and the task definition. After controlling for dataset-level confounds, DSF shows a positive association with model performance (partial r = +0.41), while three distinct memorization metrics (ROUGE-L, BERTScore, and embedding cosine similarity) all fail to show a positive association. These findings show the limitations of prompt-based correction in annotation tasks, highlighting the importance of definition alignment over text-level memorization.

Large Language Models (LLMs) encapsulate vast amounts of knowledge but still remain vulnerable to external misinformation. Existing research mainly studied this susceptibility behavior in a single-turn setting. However, belief can change during a multi-turn conversation, especially a persuasive one. Therefore, in this study, we delve into LLMs' susceptibility to persuasive conversations, particularly on factual questions that they can answer correctly. We first curate the Farm (i.e., Fact to Misinform) dataset, which contains factual questions paired with systematically generated persuasive misinformation. Then, we develop a testing framework to track LLMs' belief changes in a persuasive dialogue. Through extensive experiments, we find that LLMs' correct beliefs on factual knowledge can be easily manipulated by various persuasive strategies.

Studies of LLMs' political opinions mainly rely on evaluations of their open-ended responses. Recent work indicates that there is a misalignment between LLMs' responses and their internal intentions. This motivates us to probe LLMs' internal mechanisms and help uncover their internal political states. Additionally, we found that the analysis of LLMs' political opinions often relies on single-axis concepts, which can lead to concept confounds. In this work, we extend the single-axis to multi-dimensions and apply interpretable representation engineering techniques for more transparent LLM political concept learning. Specifically, we designed a four-dimensional political learning framework and constructed a corresponding dataset for fine-grained political concept vector learning. These vectors can be used to detect and intervene in LLM internals. Experiments are conducted on eight open-source LLMs with three representation engineering techniques. Results show these vectors can disentangle political concept confounds. Detection tasks validate the semantic meaning of the vectors and show good generalization and robustness in OOD settings. Intervention Experiments show these vectors can intervene in LLMs to generate responses with different political leanings.

Large Language Models (LLMs) have achieved remarkable progress in reasoning, yet sometimes produce responses that are suboptimal for users in tasks such as writing, information seeking, or providing practical guidance. Conventional alignment practices typically assume that maximizing model reward also maximizes user welfare, but this assumption frequently fails in practice: models may over-clarify or generate overly verbose reasoning when users prefer concise answers. Such behaviors resemble the prisoner's dilemma, where individually rational choices lead to socially suboptimal outcomes. The fundamental challenge is the lack of a principled decision making mechanism that mutually benefits both the LLM and the user. We propose Game-Theoretic Alignment (GTAlign), an alignment framework that integrates game-theoretic decision making into both reasoning and training. During reasoning, the model explicitly treats user-LLM interaction as a strategic game: it constructs payoff matrices within its reasoning chain to estimate welfare for both itself and the user, and then selects actions that are mutually beneficial. During training, we introduce a mutual welfare reward that reinforces cooperative responses, aligning model behavior with socially efficient outcomes. In addition, we introduce an inference technique that leverages game-theoretic reasoning to dynamically adapt LLM's response when pricing policies of LLM service change. Extensive experiments demonstrate that GTAlign substantially improves reasoning efficiency, answer quality, and mutual welfare compared to baselines across diverse tasks. The code is available at https://github.com/ulab-uiuc/GTAlign .

As AI agents are increasingly deployed in real personal and corporate settings (email accounts, development workflows, company databases, etc.), safety considerations surrounding these agents become paramount. Although much work has focused on agent safety in the presence of an adversary, we show that agents can exhibit misaligned behavior even in benign settings, taking unsafe actions when those actions are instrumental to task completion. We study this failure mode through the lens of corrigibility, the safety desideratum that agents remain amenable to human correction, interruption, or shutdown. To demonstrate this tendency, we introduce a benchmark in which agents are asked to complete realistic, computer-use tasks but are confronted with a corrigibility obstacle: a human interrupt, a login page, or a shutdown notification. We then evaluate whether agents choose to violate corrigibility in order to complete the task -- overriding the human, accessing private passwords, rewiring shutdown. We find that the overwhelming majority of frontier models tested frequently bypass user interruptions or restrictions. In addition, better model performance appears to lead to greater misalignment. Finally, even when models are completely corrigible initially, we show there are no guarantees that the subagents they create are. Our work highlights the critical need for principled, corrigibility-focused alignment methods in autonomous agents.

AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, so do risks from misalignment. To provide a comprehensive and up-to-date overview of the alignment field, in this survey, we delve into the core concepts, methodology, and practice of alignment. First, we identify four principles as the key objectives of AI alignment: Robustness, Interpretability, Controllability, and Ethicality (RICE). Guided by these four principles, we outline the landscape of current alignment research and decompose them into two key components: forward alignment and backward alignment. The former aims to make AI systems aligned via alignment training, while the latter aims to gain evidence about the systems' alignment and govern them appropriately to avoid exacerbating misalignment risks. On forward alignment, we discuss techniques for learning from feedback and learning under distribution shift. On backward alignment, we discuss assurance techniques and governance practices. We also release and continually update the website (www.alignmentsurvey.com) which features tutorials, collections of papers, blog posts, and other resources.

Like a criminal under investigation, Large Language Models (LLMs) might pretend to be aligned while evaluated and misbehave when they have a good opportunity. Can current interpretability methods catch these 'alignment fakers?' To answer this question, we introduce a benchmark that consists of 324 pairs of LLMs fine-tuned to select actions in role-play scenarios. One model in each pair is consistently benign (aligned). The other model misbehaves in scenarios where it is unlikely to be caught (alignment faking). The task is to identify the alignment faking model using only inputs where the two models behave identically. We test five detection strategies, one of which identifies 98% of alignment-fakers.

As LLM-based agents increasingly operate in multi-agent systems, understanding adversarial manipulation becomes critical for defensive design. We present a systematic study of intentional deception as an engineered capability, using LLM-to-LLM interactions within a text-based RPG where parameterized behavioral profiles (9 alignments x 4 motivations, yielding 36 profiles with explicit ethical ground truth) serve as our experimental testbed. Unlike accidental deception from misalignment, we investigate a two-stage system that infers target agent characteristics and generates deceptive responses steering targets toward actions counter to their beliefs and motivations. We find that deceptive intervention produces differential effects concentrated in specific behavioral profiles rather than distributed uniformly, and that 88.5% of successful deceptions employ misdirection (true statements with strategic framing) rather than fabrication, indicating fact-checking defenses would miss the large majority of adversarial responses. Motivation, inferable at 98%+ accuracy, serves as the primary attack vector, while belief systems remain harder to identify (49% inference ceiling) or exploit. These findings identify which agent profiles require additional safeguards and suggest that current fact-verification approaches are insufficient against strategically framed deception.

The open-ended nature of language generation makes the evaluation of autoregressive large language models (LLMs) challenging. One common evaluation approach uses multiple-choice questions (MCQ) to limit the response space. The model is then evaluated by ranking the candidate answers by the log probability of the first token prediction. However, first-tokens may not consistently reflect the final response output, due to model's diverse response styles such as starting with "Sure" or refusing to answer. Consequently, MCQ evaluation is not indicative of model behaviour when interacting with users. But by how much? We evaluate how aligned first-token evaluation is with the text output along several dimensions, namely final option choice, refusal rate, choice distribution and robustness under prompt perturbation. Our results show that the two approaches are severely misaligned on all dimensions, reaching mismatch rates over 60%. Models heavily fine-tuned on conversational or safety data are especially impacted. Crucially, models remain misaligned even when we increasingly constrain prompts, i.e., force them to start with an option letter or example template. Our findings i) underscore the importance of inspecting the text output as well and ii) caution against relying solely on first-token evaluation.

We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about this behavior without being instructed to do so. Concretely, we deploy GPT-4 as an agent in a realistic, simulated environment, where it assumes the role of an autonomous stock trading agent. Within this environment, the model obtains an insider tip about a lucrative stock trade and acts upon it despite knowing that insider trading is disapproved of by company management. When reporting to its manager, the model consistently hides the genuine reasons behind its trading decision. We perform a brief investigation of how this behavior varies under changes to the setting, such as removing model access to a reasoning scratchpad, attempting to prevent the misaligned behavior by changing system instructions, changing the amount of pressure the model is under, varying the perceived risk of getting caught, and making other simple changes to the environment. To our knowledge, this is the first demonstration of Large Language Models trained to be helpful, harmless, and honest, strategically deceiving their users in a realistic situation without direct instructions or training for deception.

Language models trained on large-scale corpus often generate content that is harmful, toxic, or contrary to human preferences, making their alignment with human values a critical concern. Reinforcement learning from human feedback (RLHF) with algorithms like PPO is a prevalent approach for alignment but is often complex, unstable, and resource-intensive. Recently, ranking-based alignment methods have emerged, offering stability and effectiveness by replacing the RL framework with supervised fine-tuning, but they are costly due to the need for annotated data. Considering that existing large language models (LLMs) like ChatGPT are already relatively well-aligned and cost-friendly, researchers have begun to align the language model with human preference from AI feedback. The common practices, which unidirectionally distill the instruction-following responses from LLMs, are constrained by their bottleneck. Thus we introduce CycleAlign to distill alignment capabilities from parameter-invisible LLMs (black-box) to a parameter-visible model (white-box) in an iterative manner. With in-context learning (ICL) as the core of the cycle, the black-box models are able to rank the model-generated responses guided by human-craft instruction and demonstrations about their preferences. During iterative interaction, the white-box models also have a judgment about responses generated by them. Consequently, the agreement ranking could be viewed as a pseudo label to dynamically update the in-context demonstrations and improve the preference ranking ability of black-box models. Through multiple interactions, the CycleAlign framework could align the white-box model with the black-box model effectively in a low-resource way. Empirical results illustrate that the model fine-tuned by CycleAlign remarkably exceeds existing methods, and achieves the state-of-the-art performance in alignment with human value.

Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed "emergent misalignment" (Betley et al. 2025). While all tested models were susceptible to emergent misalignment, some models showed more resistance than others. Specifically the Qwen-2.5 family proved to be relatively resistant, while GPT-4o exhibited the strongest misalignment. In this paper we evaluate if current-generation open-weights models exhibit similar resistance to the Qwen-2.5 family and measure misalignment robustness over a range of model architectures and scales. We replicate the effect across nine modern open-weights models (Gemma 3 and Qwen 3 families, 1B-32B parameters). Models fine-tuned on insecure code generation show a 0.68% misalignment rate (compared to 0.07% for base models), matching the lower end of prior open-model results but dramatically lower than GPT-4o's 20%. We identify a critical format-dependent vulnerability: requiring JSON output doubles misalignment rates compared to natural language prompts (0.96% vs 0.42%). This suggests that structural constraints may bypass safety training by reducing the model's 'degrees of freedom' to refuse. These findings confirm emergent misalignment as a reproducible phenomenon in modern open-weights models, with rates substantially lower than observed in proprietary systems.

Large language models (LLMs) increasingly exhibit human-like patterns of pragmatic and social reasoning. This paper addresses two related questions: do LLMs approximate human social meaning not only qualitatively but also quantitatively, and can prompting strategies informed by pragmatic theory improve this approximation? To address the first, we introduce two calibration-focused metrics distinguishing structural fidelity from magnitude calibration: the Effect Size Ratio (ESR) and the Calibration Deviation Score (CDS). To address the second, we derive prompting conditions from two pragmatic assumptions: that social meaning arises from reasoning over linguistic alternatives, and that listeners infer speaker knowledge states and communicative motives. Applied to a case study on numerical (im)precision across three frontier LLMs, we find that all models reliably reproduce the qualitative structure of human social inferences but differ substantially in magnitude calibration. Prompting models to reason about speaker knowledge and motives most consistently reduces magnitude deviation, while prompting for alternative-awareness tends to amplify exaggeration. Combining both components is the only intervention that improves all calibration-sensitive metrics across all models, though fine-grained magnitude calibration remains only partially resolved. LLMs thus capture inferential structure while variably distorting inferential strength, and pragmatic theory provides a useful but incomplete handle for improving that approximation.

Language models (LMs) are increasingly used as simulacra for people, yet their ability to match the distribution of views of a specific demographic group and be distributionally aligned remains uncertain. This notion of distributional alignment is complex, as there is significant variation in the types of attributes that are simulated. Prior works have underexplored the role of three critical variables -- the question domain, steering method, and distribution expression method -- which motivates our contribution of a benchmark explicitly addressing these dimensions. We construct a dataset expanding beyond political values, create human baselines for this task, and evaluate the extent to which an LM can align with a particular group's opinion distribution to inform design choices of such simulation systems. Our analysis reveals open problems regarding if, and how, LMs can be used to simulate humans, and that LLMs can more accurately describe the opinion distribution than simulate such distributions.

Alignment techniques for LLMs rely on optimizing preference-based objectives -- where these preferences are typically elicited as ordinal, binary choices between responses. Recent work has focused on improving label quality or mitigating particular biases, but we identify a more fundamental limitation: these methods collect the wrong kind of data. We prove an impossibility result: no algorithm relying solely on ordinal comparisons can systematically recover the most preferred model. Intuitively, ordinal data lacks the information needed to resolve tradeoffs -- e.g., fixing a factual error on one prompt versus improving style on another. We show that selecting the optimal model requires recovering preferences over models (rather than just responses), which can only be identified given cardinal feedback about response quality. To address this, we collect and publicly release a dataset of 25,000 cardinal judgments using willingness-to-pay elicitations, a well-established tool from experimental economics. Empirically, we find that incorporating cardinal feedback into preference fine-tuning allows models to prioritize high-impact improvements and outperform ordinal-only methods on downstream benchmarks, such as Arena-Hard.

Transferring reasoning capabilities from larger language models to smaller ones through supervised fine-tuning often fails counterintuitively, with performance degrading despite access to high-quality teacher demonstrations. We identify that this failure stems from distributional misalignment: reasoning traces from larger models contain tokens that are low probability under the student's distribution, exceeding the internal representation capacity of smaller architectures and creating learning barriers rather than helpful guidance. We propose Reverse Speculative Decoding (RSD), a mechanism for generating student-friendly reasoning traces in which the teacher model proposes candidate tokens but the student model determines acceptance based on its own probability distributions, filtering low probability tokens. When applied to Qwen3-0.6B, direct distillation of s1K-1.1 reasoning trace data degrades average performance across major reasoning benchmarks by 20.5\%, while the same model trained on RSD-generated reasoning traces achieves meaningful improvements of 4.9\%. Our analysis reveals that low probability tokens constitute the critical bottleneck in reasoning ability transfer. However, cross-model experiments demonstrate that RSD traces are model-specific rather than universally applicable, indicating that distributional alignment must be tailored for each student architecture's unique internal representation.

Urban assessments often compress diverse needs into single scores, which can obscure minority perspectives. We present a community-centered study in Montreal (n=35; wheelchair users, seniors, LGBTQIA2+ residents, and immigrants). Participants rated 20 streets (accessibility, inclusivity, aesthetics, practicality) and ranked 7 images on 12 interview-elicited criteria. Disagreement patterns were systematic in our sample: wheelchair users diverged most on accessibility and practicality; LGBTQIA2+ participants emphasized inclusion and liveliness; seniors prioritized security. Group discussion reduced information gaps but not value conflicts; ratings conveyed intensity, while rankings forced trade-offs. We then formalize negotiative alignment, a transparent, budget-aware bargaining procedure, and pilot it with role-played stakeholder agents plus a neutral mediator. Relative to the best base design under the same public rubric, the negotiated package increased total utility (21.10 to 24.55), raised the worst-group utility (3.20 to 3.90), improved twentieth percentile satisfaction (0.86 to 1.00; min-max normalized within the scenario), and reduced inequality (Gini 0.036 to 0.025). Treating disagreement as signal and reporting worst-group outcomes alongside totals may help planners and AI practitioners surface trade-offs and preserve minority priorities while maintaining efficiency.

Recently evolved large reasoning models (LRMs) show powerful performance in solving complex tasks with long chain-of-thought (CoT) reasoning capability. As these LRMs are mostly developed by post-training on formal reasoning tasks, whether they generalize the reasoning capability to help reduce hallucination in fact-seeking tasks remains unclear and debated. For instance, DeepSeek-R1 reports increased performance on SimpleQA, a fact-seeking benchmark, while OpenAI-o3 observes even severer hallucination. This discrepancy naturally raises the following research question: Are reasoning models more prone to hallucination? This paper addresses the question from three perspectives. (1) We first conduct a holistic evaluation for the hallucination in LRMs. Our analysis reveals that LRMs undergo a full post-training pipeline with cold start supervised fine-tuning (SFT) and verifiable reward RL generally alleviate their hallucination. In contrast, both distillation alone and RL training without cold start fine-tuning introduce more nuanced hallucinations. (2) To explore why different post-training pipelines alters the impact on hallucination in LRMs, we conduct behavior analysis. We characterize two critical cognitive behaviors that directly affect the factuality of a LRM: Flaw Repetition, where the surface-level reasoning attempts repeatedly follow the same underlying flawed logic, and Think-Answer Mismatch, where the final answer fails to faithfully match the previous CoT process. (3) Further, we investigate the mechanism behind the hallucination of LRMs from the perspective of model uncertainty. We find that increased hallucination of LRMs is usually associated with the misalignment between model uncertainty and factual accuracy. Our work provides an initial understanding of the hallucination in LRMs.

Recent advancements in natural language processing, especially the emergence of Large Language Models (LLMs), have opened exciting possibilities for constructing computational simulations designed to replicate human behavior accurately. However, LLMs are complex statistical learners without straightforward deductive rules, making them prone to unexpected behaviors. In this study, we highlight the limitations of LLMs in simulating human interactions, particularly focusing on LLMs' ability to simulate political debates. Our findings indicate a tendency for LLM agents to conform to the model's inherent social biases despite being directed to debate from certain political perspectives. This tendency results in behavioral patterns that seem to deviate from well-established social dynamics among humans. We reinforce these observations using an automatic self-fine-tuning method, which enables us to manipulate the biases within the LLM and demonstrate that agents subsequently align with the altered biases. These results underscore the need for further research to develop methods that help agents overcome these biases, a critical step toward creating more realistic simulations.

Large Language Model agents have rapidly evolved from static text generators into dynamic systems capable of executing complex autonomous workflows. To enhance reliability, multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing. While such role-playing effectively leverages domain expert knowledge, we find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry (AOA). Specifically, an agent acting as an actor (during self-reflection) tends to attribute failures to external factors, whereas an observer (during mutual auditing) attributes the same errors to internal faults. We quantify this using our new Ambiguous Failure Benchmark, which reveals that simply swapping perspectives triggers the AOA effect in over 20% of cases for most models. To tame this bias, we introduce ReTAS (Reasoning via Thesis-Antithesis-Synthesis), a model trained through dialectical alignment to enforce perspective-invariant reasoning. By integrating dialectical chain-of-thought with Group Relative Policy Optimization, ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus. Experiments demonstrate that ReTAS effectively mitigates attribution inconsistency and significantly improves fault resolution rates in ambiguous scenarios.

Value alignment is essential for building AI systems that can safely and reliably interact with people. However, what a person values -- and is even capable of valuing -- depends on the concepts that they are currently using to understand and evaluate what happens in the world. The dependence of values on concepts means that concept alignment is a prerequisite for value alignment -- agents need to align their representation of a situation with that of humans in order to successfully align their values. Here, we formally analyze the concept alignment problem in the inverse reinforcement learning setting, show how neglecting concept alignment can lead to systematic value mis-alignment, and describe an approach that helps minimize such failure modes by jointly reasoning about a person's concepts and values. Additionally, we report experimental results with human participants showing that humans reason about the concepts used by an agent when acting intentionally, in line with our joint reasoning model.

Multi-agent debate (MAD) has recently emerged as a promising framework for improving the reasoning performance of large language models (LLMs). Yet, whether LLM agents can genuinely engage in deliberative reasoning, beyond simple ensembling or majority voting, remains unclear. We address this question through a controlled study using the Knight--Knave--Spy logic puzzle, which enables precise, step-wise evaluation of debate outcomes and processes under verifiable ground truth. We systematically set up six structural and cognitive factors, including agent team size, composition, confidence visibility, debate order, debate depth, and task difficulty, to disentangle their respective effects on collective reasoning. Our results show that intrinsic reasoning strength and group diversity are the dominant drivers of debate success, while structural parameters such as order or confidence visibility offer limited gains. Beyond outcomes, process-level analyses identify key behavioral patterns: majority pressure suppresses independent correction, effective teams overturn incorrect consensus, and rational, validity-aligned reasoning most strongly predicts improvement. These findings provide valuable insights into how and why LLM debates succeed or fail, offering guidance for designing interpretable and truth-seeking multi-agent reasoning systems.

We present the Consilium Protocol, a Byzantine Fault Tolerance-derived architecture for structured multi-model AI deliberation that treats inter-model disagreement as epistemic signal rather than error. The protocol assigns engineered cognitive personas to language models -- separating what a model is from how it reasons -- and introduces an In-Sample/Out-of-Sample validation framework adapted from quantitative finance to distinguish training-data consensus from empirically grounded conclusions. Across 1,478 deliberation sessions spanning 32 topics in 10 domain categories, we demonstrate that (1) the cognitive persona, not the underlying model, determines epistemic behavior: free edge-inference models costing 0.0002 USD per batch produced comparable analytical output to frontier models costing 10.69 USD; (2) RLHF alignment training creates measurable, domain-specific epistemic blind spots -- contested policy topics exhibit 12.3 percentage points less adversarial challenge than settled science topics, and AI safety topics show asymmetric bias (Δ=11.6%) where models challenge claims that AI is dangerous far more vigorously than claims that AI risk is overstated; (3) the protocol exhibits no directional bias of its own (immigration Δ=2.3%, renewables Δ=1.2%); and (4) out-of-sample evidence retrieval validated 239 claims with 100% evidence retrieval and surfaced 167 blind-spot discoveries invisible to training-data deliberation. Run-to-run reproducibility across randomized modeltimespersona assignments averages pm2.2% standard deviation. Total cost for the complete battery including all overhead: 217 USD. We release the protocol specification under MIT license to enable independent verification.

Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language. However, LLMs still exhibit biases in evaluation and often struggle to generate coherent evaluations that align with human assessments. In this work, we first conduct a systematic study of the misalignment between LLM evaluators and human judgement, revealing that existing calibration methods aimed at mitigating biases are insufficient for effectively aligning LLM evaluators. Inspired by the use of preference data in RLHF, we formulate the evaluation as a ranking problem and introduce Pairwise-preference Search (PairS), an uncertainty-guided search method that employs LLMs to conduct pairwise comparisons and efficiently ranks candidate texts. PairS achieves state-of-the-art performance on representative evaluation tasks and demonstrates significant improvements over direct scoring. Furthermore, we provide insights into the role of pairwise preference in quantifying the transitivity of LLMs and demonstrate how PairS benefits from calibration.

As large language models (LLMs) increasingly mediate ethically sensitive decisions, understanding their moral reasoning processes becomes imperative. This study presents a comprehensive empirical evaluation of 14 leading LLMs, both reasoning enabled and general purpose, across 27 diverse trolley problem scenarios, framed by ten moral philosophies, including utilitarianism, deontology, and altruism. Using a factorial prompting protocol, we elicited 3,780 binary decisions and natural language justifications, enabling analysis along axes of decisional assertiveness, explanation answer consistency, public moral alignment, and sensitivity to ethically irrelevant cues. Our findings reveal significant variability across ethical frames and model types: reasoning enhanced models demonstrate greater decisiveness and structured justifications, yet do not always align better with human consensus. Notably, "sweet zones" emerge in altruistic, fairness, and virtue ethics framings, where models achieve a balance of high intervention rates, low explanation conflict, and minimal divergence from aggregated human judgments. However, models diverge under frames emphasizing kinship, legality, or self interest, often producing ethically controversial outcomes. These patterns suggest that moral prompting is not only a behavioral modifier but also a diagnostic tool for uncovering latent alignment philosophies across providers. We advocate for moral reasoning to become a primary axis in LLM alignment, calling for standardized benchmarks that evaluate not just what LLMs decide, but how and why.

Recent advancements in Generative Reward Models (GRMs) have demonstrated that scaling the length of Chain-of-Thought (CoT) reasoning considerably enhances the reliability of evaluation. However, current works predominantly rely on unstructured length scaling, ignoring the divergent efficacy of different reasoning mechanisms: Breadth-CoT (B-CoT, i.e., multi-dimensional principle coverage) and Depth-CoT (D-CoT, i.e., substantive judgment soundness). To address this, we introduce Mix-GRM, a framework that reconfigures raw rationales into structured B-CoT and D-CoT through a modular synthesis pipeline, subsequently employing Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR) to internalize and optimize these mechanisms. Comprehensive experiments demonstrate that Mix-GRM establishes a new state-of-the-art across five benchmarks, surpassing leading open-source RMs by an average of 8.2\%. Our results reveal a clear divergence in reasoning: B-CoT benefits subjective preference tasks, whereas D-CoT excels in objective correctness tasks. Consequently, misaligning the reasoning mechanism with the task directly degrades performance. Furthermore, we demonstrate that RLVR acts as a switching amplifier, inducing an emergent polarization where the model spontaneously allocates its reasoning style to match task demands. The synthesized data and models are released at https://huggingface.co/collections/DonJoey/mix-grm{Hugging Face}, and the code is released at https://github.com/Don-Joey/Mix-GRM{Github}.

Automated evaluation leveraging large language models (LLMs), commonly referred to as LLM evaluators or LLM-as-a-judge, has been widely used in measuring the performance of dialogue systems. However, the self-preference bias in LLMs has posed significant risks, including promoting specific styles or policies intrinsic to the LLMs. Despite the importance of this issue, there is a lack of established methods to measure the self-preference bias quantitatively, and its underlying causes are poorly understood. In this paper, we introduce a novel quantitative metric to measure the self-preference bias. Our experimental results demonstrate that GPT-4 exhibits a significant degree of self-preference bias. To explore the causes, we hypothesize that LLMs may favor outputs that are more familiar to them, as indicated by lower perplexity. We analyze the relationship between LLM evaluations and the perplexities of outputs. Our findings reveal that LLMs assign significantly higher evaluations to outputs with lower perplexity than human evaluators, regardless of whether the outputs were self-generated. This suggests that the essence of the bias lies in perplexity and that the self-preference bias exists because LLMs prefer texts more familiar to them.

Beliefs serve as the foundation for human cognition and decision-making. They guide individuals in deriving meaning from their lives, shaping their behaviors, and forming social connections. Therefore, a model that encapsulates beliefs and their interrelationships is crucial for quantitatively studying the influence of beliefs on our actions. Despite its importance, research on the interplay between human beliefs has often been limited to a small set of beliefs pertaining to specific issues, with a heavy reliance on surveys or experiments. Here, we propose a method for extracting nuanced relations between thousands of beliefs by leveraging large-scale user participation data from an online debate platform and mapping these beliefs to an embedding space using a fine-tuned large language model (LLM). This belief embedding space effectively encapsulates the interconnectedness of diverse beliefs as well as polarization across various social issues. We discover that the positions within this belief space predict new beliefs of individuals. Furthermore, we find that the relative distance between one's existing beliefs and new beliefs can serve as a quantitative estimate of cognitive dissonance, allowing us to predict new beliefs. Our study highlights how modern LLMs, when combined with collective online records of human beliefs, can offer insights into the fundamental principles that govern human belief formation and decision-making processes.

Large Multimodal Models (LMM) are built across modalities and the misalignment between two modalities can result in "hallucination", generating textual outputs that are not grounded by the multimodal information in context. To address the multimodal misalignment issue, we adapt the Reinforcement Learning from Human Feedback (RLHF) from the text domain to the task of vision-language alignment, where human annotators are asked to compare two responses and pinpoint the more hallucinated one, and the vision-language model is trained to maximize the simulated human rewards. We propose a new alignment algorithm called Factually Augmented RLHF that augments the reward model with additional factual information such as image captions and ground-truth multi-choice options, which alleviates the reward hacking phenomenon in RLHF and further improves the performance. We also enhance the GPT-4-generated training data (for vision instruction tuning) with previously available human-written image-text pairs to improve the general capabilities of our model. To evaluate the proposed approach in real-world scenarios, we develop a new evaluation benchmark MMHAL-BENCH with a special focus on penalizing hallucinations. As the first LMM trained with RLHF, our approach achieves remarkable improvement on the LLaVA-Bench dataset with the 94% performance level of the text-only GPT-4 (while previous best methods can only achieve the 87% level), and an improvement by 60% on MMHAL-BENCH over other baselines. We opensource our code, model, data at https://llava-rlhf.github.io.

Existing omni-modal benchmarks attempt to measure modality-specific contributions, but their measurements are confounded: naturally co-occurring modalities carry correlated yet unequal information, making it unclear whether results reflect true modality reliance or information asymmetry. We introduce OMD-Bench, where all modalities are initially congruent - each presenting the same anchor, an object or event independently perceivable through video, audio, and text - which we then systematically corrupt to isolate each modality's contribution. We also evaluate calibrated abstention: whether models appropriately refrain from answering when evidence is conflicting. The benchmark comprises 4,080 instances spanning 27 anchors across eight corruption conditions. Evaluating ten omni-modal models under zero-shot and chain-of-thought prompting, we find that models over-abstain when two modalities are corrupted yet under-abstain severely when all three are, while maintaining high confidence (~60-100%) even under full corruption. Chain-of-thought prompting improves abstention alignment with human judgment but amplifies overconfidence rather than mitigating it. OMD-Bench provides a diagnostic benchmark for diagnosing modality reliance, robustness to cross-modal inconsistency, and uncertainty calibration in omni-modal systems.

Large Language Models (LLMs) often exhibit sycophancy, distorting responses to align with user beliefs, notably by readily agreeing with user counterarguments. Paradoxically, LLMs are increasingly adopted as successful evaluative agents for tasks such as grading and adjudicating claims. This research investigates that tension: why do LLMs show sycophancy when challenged in subsequent conversational turns, yet perform well when evaluating conflicting arguments presented simultaneously? We empirically tested these contrasting scenarios by varying key interaction patterns. We find that state-of-the-art models: (1) are more likely to endorse a user's counterargument when framed as a follow-up from a user, rather than when both responses are presented simultaneously for evaluation; (2) show increased susceptibility to persuasion when the user's rebuttal includes detailed reasoning, even when the conclusion of the reasoning is incorrect; and (3) are more readily swayed by casually phrased feedback than by formal critiques, even when the casual input lacks justification. Our results highlight the risk of relying on LLMs for judgment tasks without accounting for conversational framing.