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.
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.
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.
Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism
Large language models (LLMs) have demonstrated impressive language understanding and generation capabilities, enabling them to answer a wide range of questions across various domains. However, these models are not flawless and often produce responses that contain errors or misinformation. These inaccuracies, commonly referred to as hallucinations, render LLMs unreliable and even unusable in many scenarios. In this paper, our focus is on mitigating the issue of hallucination in LLMs, particularly in the context of question-answering. Instead of attempting to answer all questions, we explore a refusal mechanism that instructs LLMs to refuse to answer challenging questions in order to avoid errors. We then propose a simple yet effective solution called Learn to Refuse (L2R), which incorporates the refusal mechanism to enable LLMs to recognize and refuse to answer questions that they find difficult to address. To achieve this, we utilize a structured knowledge base to represent all the LLM's understanding of the world, enabling it to provide traceable gold knowledge. This knowledge base is separate from the LLM and initially empty. It can be filled with validated knowledge and progressively expanded. When an LLM encounters questions outside its domain, the system recognizes its knowledge scope and determines whether it can answer the question independently. Additionally, we introduce a method for automatically and efficiently expanding the knowledge base of LLMs. Through qualitative and quantitative analysis, we demonstrate that our approach enhances the controllability and reliability of LLMs.
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.
OpenAI admits AI hallucinations are mathematically inevitable, not just engineering flaws
In a landmark study, OpenAI researchers reveal that large language models will always produce plausible but false outputs, even with perfect data, due to fundamental statistical and computational limits.
Knowledge Collapse in LLMs: When Fluency Survives but Facts Fail under Recursive Synthetic Training
Large language models increasingly rely on synthetic data due to human-written content scarcity, yet recursive training on model-generated outputs leads to model collapse, a degenerative process threatening factual reliability. We define knowledge collapse as a distinct three-stage phenomenon where factual accuracy deteriorates while surface fluency persists, creating "confidently wrong" outputs that pose critical risks in accuracy-dependent domains. Through controlled experiments with recursive synthetic training, we demonstrate that collapse trajectory and timing depend critically on instruction format, distinguishing instruction-following collapse from traditional model collapse through its conditional, prompt-dependent nature. We propose domain-specific synthetic training as a targeted mitigation strategy that achieves substantial improvements in collapse resistance while maintaining computational efficiency. Our evaluation framework combines model-centric indicators with task-centric metrics to detect distinct degradation phases, enabling reproducible assessment of epistemic deterioration across different language models. These findings provide both theoretical insights into collapse dynamics and practical guidance for sustainable AI training in knowledge-intensive applications where accuracy is paramount.
Knowledge Collapse in LLMs: When Fluency Survives but Facts Fail under Recursive Synthetic Training
Large language models increasingly rely on synthetic data due to human-written content scarcity, yet recursive training on model-generated outputs leads to model collapse, a degenerative process threatening factual reliability. We define knowledge collapse as a distinct three-stage phenomenon where factual accuracy deteriorates while surface fluency persists, creating "confidently wrong" outputs that pose critical risks in accuracy-dependent domains. Through controlled experiments with recursive synthetic training, we demonstrate that collapse trajectory and timing depend critically on instruction format, distinguishing instruction-following collapse from traditional model collapse through its conditional, prompt-dependent nature. We propose domain-specific synthetic training as a targeted mitigation strategy that achieves substantial improvements in collapse resistance while maintaining computational efficiency. Our evaluation framework combines model-centric indicators with task-centric metrics to detect distinct degradation phases, enabling reproducible assessment of epistemic deterioration across different language models. These findings provide both theoretical insights into collapse dynamics and practical guidance for sustainable AI training in knowledge-intensive applications where accuracy is paramount.
Reasoning Models Don't Always Say What They Think
Chain-of-thought (CoT) offers a potential boon for AI safety as it allows monitoring a model's CoT to try to understand its intentions and reasoning processes. However, the effectiveness of such monitoring hinges on CoTs faithfully representing models' actual reasoning processes. We evaluate CoT faithfulness of state-of-the-art reasoning models across 6 reasoning hints presented in the prompts and find: (1) for most settings and models tested, CoTs reveal their usage of hints in at least 1% of examples where they use the hint, but the reveal rate is often below 20%, (2) outcome-based reinforcement learning initially improves faithfulness but plateaus without saturating, and (3) when reinforcement learning increases how frequently hints are used (reward hacking), the propensity to verbalize them does not increase, even without training against a CoT monitor. These results suggest that CoT monitoring is a promising way of noticing undesired behaviors during training and evaluations, but that it is not sufficient to rule them out. They also suggest that in settings like ours where CoT reasoning is not necessary, test-time monitoring of CoTs is unlikely to reliably catch rare and catastrophic unexpected behaviors.
Reasoning Models Don't Always Say What They Think
Chain-of-thought (CoT) offers a potential boon for AI safety as it allows monitoring a model's CoT to try to understand its intentions and reasoning processes. However, the effectiveness of such monitoring hinges on CoTs faithfully representing models' actual reasoning processes. We evaluate CoT faithfulness of state-of-the-art reasoning models across 6 reasoning hints presented in the prompts and find: (1) for most settings and models tested, CoTs reveal their usage of hints in at least 1% of examples where they use the hint, but the reveal rate is often below 20%, (2) outcome-based reinforcement learning initially improves faithfulness but plateaus without saturating, and (3) when reinforcement learning increases how frequently hints are used (reward hacking), the propensity to verbalize them does not increase, even without training against a CoT monitor. These results suggest that CoT monitoring is a promising way of noticing undesired behaviors during training and evaluations, but that it is not sufficient to rule them out. They also suggest that in settings like ours where CoT reasoning is not necessary, test-time monitoring of CoTs is unlikely to reliably catch rare and catastrophic unexpected behaviors.
AI hallucinations are getting worse – and they're here to stay
An AI leaderboard suggests the newest reasoning models used in chatbots are producing less accurate results because of higher hallucination rates. Experts say the problem is bigger than that
What are AI hallucinations? Why AIs sometimes make things up
When AI systems try to bridge gaps in their training data, the results can be wildly off the mark: fabrications and non sequiturs researchers call hallucinations.
What are AI hallucinations? Why AIs sometimes make things up
When AI systems try to bridge gaps in their training data, the results can be wildly off the mark: fabrications and non sequiturs researchers call hallucinations.
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.
“Hallucinating” AI models help coin Cambridge Dictionary’s word of the year
Cambridge: "When an artificial intelligence hallucinates, it produces false information."
