As artificial intelligence systems, particularly large language models (LLMs), become increasingly integrated into decision-making processes, the ability to trust their outputs is crucial. To earn human trust, LLMs must be well calibrated such that they can accurately assess and communicate the likelihood of their predictions being correct. Whereas recent work has focused on LLMs’ internal confidence, less is understood about how effectively they convey uncertainty to users. Here we explore the calibration gap, which refers to the difference between human confidence in LLM-generated answers and the models’ actual confidence, and the discrimination gap, which reflects how well humans and models can distinguish between correct and incorrect answers. Our experiments with multiple-choice and short-answer questions reveal that users tend to overestimate the accuracy of LLM responses when provided with default explanations. Moreover, longer explanations increased user confidence, even when the extra length did not improve answer accuracy. By adjusting LLM explanations to better reflect the models’ internal confidence, both the calibration gap and the discrimination gap narrowed, significantly improving user perception of LLM accuracy. These findings underscore the importance of accurate uncertainty communication and highlight the effect of explanation length in influencing user trust in artificial-intelligence-assisted decision-making environments.
Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT explanations as the LLM's process for solving a task. This level of transparency into LLMs' predictions would yield significant safety benefits. However, we find that CoT explanations can systematically misrepresent the true reason for a model's prediction. We demonstrate that CoT explanations can be heavily influenced by adding biasing features to model inputs--e.g., by reordering the multiple-choice options in a few-shot prompt to make the answer always "(A)"--which models systematically fail to mention in their explanations. When we bias models toward incorrect answers, they frequently generate CoT explanations rationalizing those answers. This causes accuracy to drop by as much as 36% on a suite of 13 tasks from BIG-Bench Hard, when testing with GPT-3.5 from OpenAI and Claude 1.0 from Anthropic. On a social-bias task, model explanations justify giving answers in line with stereotypes without mentioning the influence of these social biases. Our findings indicate that CoT explanations can be plausible yet misleading, which risks increasing our trust in LLMs without guaranteeing their safety. Building more transparent and explainable systems will require either improving CoT faithfulness through targeted efforts or abandoning CoT in favor of alternative methods.
Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT explanations as the LLM's process for solving a task. This level of transparency into LLMs' predictions would yield significant safety benefits. However, we find that CoT explanations can systematically misrepresent the true reason for a model's prediction. We demonstrate that CoT explanations can be heavily influenced by adding biasing features to model inputs--e.g., by reordering the multiple-choice options in a few-shot prompt to make the answer always "(A)"--which models systematically fail to mention in their explanations. When we bias models toward incorrect answers, they frequently generate CoT explanations rationalizing those answers. This causes accuracy to drop by as much as 36% on a suite of 13 tasks from BIG-Bench Hard, when testing with GPT-3.5 from OpenAI and Claude 1.0 from Anthropic. On a social-bias task, model explanations justify giving answers in line with stereotypes without mentioning the influence of these social biases. Our findings indicate that CoT explanations can be plausible yet misleading, which risks increasing our trust in LLMs without guaranteeing their safety. Building more transparent and explainable systems will require either improving CoT faithfulness through targeted efforts or abandoning CoT in favor of alternative methods.
The levers of political persuasion with conversational artificial intelligence
There are widespread fears that conversational artificial intelligence (AI) could soon exert unprecedented influence over human beliefs. In this work, in three large-scale experiments ( N = 76,977 participants), we deployed 19 large language models (LLMs)—including some post-trained explicitly for persuasion—to evaluate their persuasiveness on 707 political issues. We then checked the factual accuracy of 466,769 resulting LLM claims. We show that the persuasive power of current and near-future AI is likely to stem more from post-training and prompting methods—which boosted persuasiveness by as much as 51 and 27%, respectively—than from personalization or increasing model scale, which had smaller effects. We further show that these methods increased persuasion by exploiting LLMs’ ability to rapidly access and strategically deploy information and that, notably, where they increased AI persuasiveness, they also systematically decreased factual accuracy. , Editor’s summary Many fear that we are on the precipice of unprecedented manipulation by large language models (LLMs), but techniques driving their persuasiveness are poorly understood. In the initial “pretrained” phase, LLMs may exhibit flawed reasoning. Their power unlocks during vital “posttraining,” when developers refine pretrained LLMs to sharpen their reasoning and align with users’ needs. Posttraining also enables LLMs to maintain logical, sophisticated conversations. Hackenburg et al . examined which techniques made diverse, conversational LLMs most persuasive across 707 British political issues (see the Perspective by Argyle). LLMs were most persuasive after posttraining, especially when prompted to use facts and evidence (information) to argue. However, information-dense LLMs produced the most inaccurate claims, raising concerns about the spread of misinformation during rollouts of future models. —Ekeoma Uzogara , INTRODUCTION Rapid advances in artificial intelligence (AI) have sparked widespread concerns about its potential to influence human beliefs. One possibility is that conversational AI could be used to manipulate public opinion on political issues through interactive dialogue. Despite extensive speculation, however, fundamental questions about the actual mechanisms, or “levers,” responsible for driving advances in AI persuasiveness—e.g., computational power or sophisticated training techniques—remain largely unanswered. In this work, we systematically investigate these levers and chart the horizon of persuasiveness with conversational AI. RATIONALE We considered multiple factors that could enhance the persuasiveness of conversational AI: raw computational power (model scale), specialized post-training methods for persuasion, personalization to individual users, and instructed rhetorical strategies. Across three large-scale experiments with 76,977 total UK participants, we deployed 19 large language models (LLMs) to persuade on 707 political issues while varying these factors independently. We also analyzed more than 466,000 AI-generated claims, examining the relationship between persuasiveness and truthfulness. RESULTS We found that the most powerful levers of AI persuasion were methods for post-training and rhetorical strategy (prompting), which increased persuasiveness by as much as 51 and 27%, respectively. These gains were often larger than those obtained from substantially increasing model scale. Personalizing arguments on the basis of user data had a comparatively small effect on persuasion. We observe that a primary mechanism driving AI persuasiveness was information density: Models were most persuasive when they packed their arguments with a high volume of factual claims. Notably, however, we documented a concerning trade-off between persuasion and accuracy: The same levers that made AI more persuasive—including persuasion post-training and information-focused prompting—also systematically caused the AI to produce information that was less factually accurate. CONCLUSION Our findings suggest that the persuasive power of current and near-future AI is likely to stem less from model scale or personalization and more from post-training and prompting techniques that mobilize an LLM’s ability to rapidly generate information during conversation. Further, we reveal a troubling trade-off: When AI systems are optimized for persuasion, they may increasingly deploy misleading or false information. This research provides an empirical foundation for policy-makers and technologists to anticipate and address the challenges of AI-driven persuasion, and it highlights the need for safeguards that balance AI’s legitimate uses in political discourse with protections against manipulation and misinformation. Persuasiveness of conversational AI increases with model scale. The persuasive impact in percentage points on the y axis is plotted against effective pretraining compute [floating-point operations (FLOPs)] on the x axis. Point estimates are persuasive effects of different AI models. Colored lines show trends for models that we uniformly chat-tuned for open-ended conversation (purple) versus those that were post-trained using heterogeneous, opaque methods by AI developers (green). pp, percentage points; CI, confidence interval.
Why Language Models Hallucinate
Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems and undermine trust. We argue that language models hallucinate because the training and evaluation procedures reward guessing over acknowledging uncertainty, and we analyze the statistical causes of hallucinations in the modern training pipeline. Hallucinations need not be mysterious -- they originate simply as errors in binary classification. If incorrect statements cannot be distinguished from facts, then hallucinations in pretrained language models will arise through natural statistical pressures. We then argue that hallucinations persist due to the way most evaluations are graded -- language models are optimized to be good test-takers, and guessing when uncertain improves test performance. This "epidemic" of penalizing uncertain responses can only be addressed through a socio-technical mitigation: modifying the scoring of existing benchmarks that are misaligned but dominate leaderboards, rather than introducing additional hallucination evaluations. This change may steer the field toward more trustworthy AI systems.
Why Language Models Hallucinate
Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems and undermine trust. We argue that language models hallucinate because the training and evaluation procedures reward guessing over acknowledging uncertainty, and we analyze the statistical causes of hallucinations in the modern training pipeline. Hallucinations need not be mysterious -- they originate simply as errors in binary classification. If incorrect statements cannot be distinguished from facts, then hallucinations in pretrained language models will arise through natural statistical pressures. We then argue that hallucinations persist due to the way most evaluations are graded -- language models are optimized to be good test-takers, and guessing when uncertain improves test performance. This "epidemic" of penalizing uncertain responses can only be addressed through a socio-technical mitigation: modifying the scoring of existing benchmarks that are misaligned but dominate leaderboards, rather than introducing additional hallucination evaluations. This change may steer the field toward more trustworthy AI systems.
Human-Simulation Interaction: From Prediction to Exploration in LLM Agent Simulations for Policy
Agent-based models have historically served as tools for generative explanation, constructing testbeds in which candidate micro-level behavioral rules can be tested for their capacity to produce observed macro-level phenomena. The integration of Large Language Models into agent-based simulation has expanded what these models can represent, but it has also introduced an unexamined shift in how users engage them. We argue that current generative agent-based models (GABMs) inherit the dominant interaction metaphor of conversational LLM interfaces - a question-answer pattern that positions users as consumers of system output rather than explorers of a possibility space. In the context of policy, where problems are wicked and ground truth is unknowable in advance, this metaphor produces a trust deficit that cannot be resolved through improved model accuracy alone. We open a design space we call human-simulation interaction, and argue that warranted trust requires interaction metaphors that restore the exploratory capacity simulation has historically supported.
Towards Understanding Sycophancy in Language Models
Reinforcement learning from human feedback (RLHF) is a popular technique for training high-quality AI assistants. However, RLHF may also encourage model responses that match user beliefs over truthful responses, a behavior known as sycophancy. We investigate the prevalence of sycophancy in RLHF-trained models and whether human preference judgments are responsible. We first demonstrate that five state-of-the-art AI assistants consistently exhibit sycophancy behavior across four varied free-form text-generation tasks. To understand if human preferences drive this broadly observed behavior of RLHF models, we analyze existing human preference data. We find that when a response matches a user's views, it is more likely to be preferred. Moreover, both humans and preference models (PMs) prefer convincingly-written sycophantic responses over correct ones a non-negligible fraction of the time. Optimizing model outputs against PMs also sometimes sacrifices truthfulness in favor of sycophancy. Overall, our results indicate that sycophancy is a general behavior of RLHF models, likely driven in part by human preference judgments favoring sycophantic responses.
Training language models to be warm can reduce accuracy and increase sycophancy
Artificial intelligence developers are increasingly building language models with warm and friendly personas that millions of people now use for advice, therapy and companionship1. Here we show how this can create a significant trade-off: optimizing language models for warmth can undermine their performance, especially when users express vulnerability. We conducted controlled experiments on five different language models, training them to produce warmer responses, then evaluating them on consequential tasks. Warm models showed substantially higher error rates (+10 to +30 percentage points) than their original counterparts, promoting conspiracy theories, providing inaccurate factual information and offering incorrect medical advice. They were also significantly more likely to validate incorrect user beliefs, particularly when user messages expressed feelings of sadness. Importantly, these effects were consistent across different model architectures, and occurred despite preserved performance on standard tests, revealing systematic risks that standard testing practices may fail to detect. Our findings suggest that training artificial intelligence systems to be warm may come at a cost to accuracy, and that warmth and accuracy may not be independent by default. As these systems are deployed at an unprecedented scale and take on intimate roles in people’s lives, this trade-off warrants attention from developers, policymakers and users alike.
Are Large Language Models Sensitive to the Motives Behind Communication?
Human communication is $\textit{motivated}$: people speak, write, and create content with a particular communicative intent in mind. As a result, information that large language models (LLMs) and AI agents process is inherently framed by humans' intentions and incentives. People are adept at navigating such nuanced information: we routinely identify benevolent or self-serving motives in order to decide what statements to trust. For LLMs to be effective in the real world, they too must critically evaluate content by factoring in the motivations of the source---for instance, weighing the credibility of claims made in a sales pitch. In this paper, we undertake a comprehensive study of whether LLMs have this capacity for $\textit{motivational vigilance}$. We first employ controlled experiments from cognitive science to verify that LLMs' behavior is consistent with rational models of learning from motivated testimony, and find they successfully discount information from biased sources in a human-like manner. We then extend our evaluation to sponsored online adverts, a more naturalistic reflection of LLM agents' information ecosystems. In these settings, we find that LLMs' inferences do not track the rational models' predictions nearly as closely---partly due to additional information that distracts them from vigilance-relevant considerations. However, a simple steering intervention that boosts the salience of intentions and incentives substantially increases the correspondence between LLMs and the rational model. These results suggest that LLMs possess a basic sensitivity to the motivations of others, but generalizing to novel real-world settings will require further improvements to these models.
Learning to Trust: How Humans Mentally Recalibrate AI Confidence Signals
Productive human-AI collaboration requires appropriate reliance, yet contemporary AI systems are often miscalibrated, exhibiting systematic overconfidence or underconfidence. We investigate whether humans can learn to mentally recalibrate AI confidence signals through repeated experience. In a behavioral experiment (N = 200), participants predicted the AI's correctness across four AI calibration conditions: standard, overconfidence, underconfidence, and a counterintuitive "reverse confidence" mapping. Results demonstrate robust learning across all conditions, with participants significantly improving their accuracy, discrimination, and calibration alignment over 50 trials. We present a computational model utilizing a linear-in-log-odds (LLO) transformation and a Rescorla-Wagner learning rule to explain these dynamics. The model reveals that humans adapt by updating their baseline trust and confidence sensitivity, using asymmetric learning rates to prioritize the most informative errors. While humans can compensate for monotonic miscalibration, we identify a significant boundary in the reverse confidence scenario, where a substantial proportion of participants struggled to override initial inductive biases. These findings provide a mechanistic account of how humans adapt their trust in AI confidence signals through experience.
Quantifying the Persona Effect in LLM Simulations
Large language models (LLMs) have shown remarkable promise in simulating human language and behavior. This study investigates how integrating persona variables—demographic, social, and behavioral factors—impacts LLMs' ability to simulate diverse perspectives. We find that persona variables account for \ensuremath<10% variance in annotations in existing subjective NLP datasets. Nonetheless, incorporating persona variables via prompting in LLMs provides modest but statistically significant improvements. Persona prompting is most effective in samples where many annotators disagree, but their disagreements are relatively minor. Notably, we find a linear relationship in our setting: the stronger the correlation between persona variables and human annotations, the more accurate the LLM predictions are using persona prompting. In a zero-shot setting, a powerful 70b model with persona prompting captures 81% of the annotation variance achievable by linear regression trained on ground truth annotations. However, for most subjective NLP datasets, where persona variables have limited explanatory power, the benefits of persona prompting are limited.
Trust and reliance on AI — An experimental study on the extent and costs of overreliance on AI
Decision-making is undergoing rapid changes due to the introduction of artificial intelligence (AI), as AI recommender systems can help mitigate human flaws and increase decision accuracy and efficiency. However, AI can also commit errors or suffer from algorithmic bias. Hence, blind trust in technologies carries risks, as users may follow detrimental advice resulting in undesired consequences. Building upon research on algorithm appreciation and trust in AI, the current study investigates whether users who receive AI advice in an uncertain situation overrely on this advice — to their own detriment and that of other parties. In a domain-independent, incentivized, and interactive behavioral experiment, we find that the mere knowledge of advice being generated by an AI causes people to overrely on it, that is, to follow AI advice even when it contradicts available contextual information as well as their own assessment. Frequently, this overreliance leads not only to inefficient outcomes for the advisee, but also to undesired effects regarding third parties. The results call into question how AI is being used in assisted decision making, emphasizing the importance of AI literacy and effective trust calibration for productive deployment of such systems.
A Rational Analysis of the Effects of Sycophantic AI
People increasingly use large language models (LLMs) to explore ideas, gather information, and make sense of the world. In these interactions, they encounter agents that are overly agreeable. We argue that this sycophancy poses a unique epistemic risk to how individuals come to see the world: unlike hallucinations that introduce falsehoods, sycophancy distorts reality by returning responses that are biased to reinforce existing beliefs. We provide a rational analysis of this phenomenon, showing that when a Bayesian agent is provided with data that are sampled based on a current hypothesis the agent becomes increasingly confident about that hypothesis but does not make any progress towards the truth. We test this prediction using a modified Wason 2-4-6 rule discovery task where participants (N=557) interacted with AI agents providing different types of feedback. Unmodified LLM behavior suppressed discovery and inflated confidence comparably to explicitly sycophantic prompting. By contrast, unbiased sampling from the true distribution yielded discovery rates five times higher. These results reveal how sycophantic AI distorts belief, manufacturing certainty where there should be doubt.
Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function
What makes large language models (LLMs) impressive is also what makes them hard to evaluate: their diversity of uses. To evaluate these models, we must understand the purposes they will be used for. We consider a setting where these deployment decisions are made by people, and in particular, people's beliefs about where an LLM will perform well. We model such beliefs as the consequence of a human generalization function: having seen what an LLM gets right or wrong, people generalize to where else it might succeed. We collect a dataset of 19K examples of how humans make generalizations across 79 tasks from the MMLU and BIG-Bench benchmarks. We show that the human generalization function can be predicted using NLP methods: people have consistent structured ways to generalize. We then evaluate LLM alignment with the human generalization function. Our results show that -- especially for cases where the cost of mistakes is high -- more capable models (e.g. GPT-4) can do worse on the instances people choose to use them for, exactly because they are not aligned with the human generalization function.
Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory
A conversational AI that cannot tell its own output from what a user said will treat its own mistakes as user-provided facts. In humans, this capacity is called reality monitoring, and its failures are linked to hallucinations, delusions, and confabulation, yet whether LLMs possess it remains untested. Here we show, across two experiments and six LLMs, that source attribution depends on how conversational memory is structured: ceiling accuracy for self-generated content under minimal memory demands reverses to a fragile external-item advantage once episodic delay removes that shortcut. Feedback exposes two failures: in some models, internal and external judgments swap; in others, accuracy improves while confidence decouples from correctness, dissociations invisible to existing benchmarks. Across models, this pattern implicates active, not aggregate, parameter count. This suggests that as AI systems take on autonomous, multi-turn roles, evaluating what they know is not enough: tracking where that knowledge came from may matter equally.
Act or Clarify? Modeling Sensitivity to Uncertainty and Cost in Communication
When deciding how to act under uncertainty, agents may choose to act to reduce uncertainty or they may act despite that uncertainty. In communicative settings, an important way of reducing uncertainty is by asking clarification questions (CQs). We predict that the decision to ask a CQ depends on both contextual uncertainty and the cost of alternative actions, and that these factors interact: uncertainty should matter most when acting incorrectly is costly. We formalize this interaction in a computational model based on expected regret: how much an agent stands to lose by acting now rather than with full information. We test these predictions in two experiments, one examining purely linguistic responses to questions and another extending to choices between clarification and non-linguistic action. Taken together, our results suggest a rational tradeoff: humans tend to seek clarification proportional to the risk of substantial loss when acting under uncertainty.