Evidence for Limited Metacognition in LLMs

• URL: http://arxiv.org/abs/2509.21545v1
• Date: Thu, 25 Sep 2025 20:30:15 GMT
• Title: Evidence for Limited Metacognition in LLMs
• Authors: Christopher Ackerman,
• Abstract summary: We introduce a novel methodology for quantitatively evaluating metacognitive abilities in LLMs.<n>Taking inspiration from research on metacognition in nonhuman animals, our approach eschews model self-reports and instead tests to what degree models can strategically deploy knowledge of internal states.
• Score: 2.538209532048867
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The possibility of LLM self-awareness and even sentience is gaining increasing public attention and has major safety and policy implications, but the science of measuring them is still in a nascent state. Here we introduce a novel methodology for quantitatively evaluating metacognitive abilities in LLMs. Taking inspiration from research on metacognition in nonhuman animals, our approach eschews model self-reports and instead tests to what degree models can strategically deploy knowledge of internal states. Using two experimental paradigms, we demonstrate that frontier LLMs introduced since early 2024 show increasingly strong evidence of certain metacognitive abilities, specifically the ability to assess and utilize their own confidence in their ability to answer factual and reasoning questions correctly and the ability to anticipate what answers they would give and utilize that information appropriately. We buttress these behavioral findings with an analysis of the token probabilities returned by the models, which suggests the presence of an upstream internal signal that could provide the basis for metacognition. We further find that these abilities 1) are limited in resolution, 2) emerge in context-dependent manners, and 3) seem to be qualitatively different from those of humans. We also report intriguing differences across models of similar capabilities, suggesting that LLM post-training may have a role in developing metacognitive abilities.

Related papers

• UniCog: Uncovering Cognitive Abilities of LLMs through Latent Mind Space Analysis [69.50752734049985]
  A growing body of research suggests that the cognitive processes of large language models (LLMs) differ fundamentally from those of humans.<n>We propose UniCog, a unified framework that analyzes LLM cognition via a latent mind space.
  arXiv  Detail & Related papers  (2026-01-25T16:19:00Z)
• Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations [1.0485739694839669]
  Large language models (LLMs) can sometimes report the strategies they actually use to solve tasks, but they can also fail to do so.<n>This suggests some degree of metacognition -- the capacity to monitor one's own cognitive processes for subsequent reporting and self-control.<n>We introduce a neuroscience-inspired neurofeedback paradigm designed to quantify the ability of LLMs to explicitly report and control their activation patterns.
  arXiv  Detail & Related papers  (2025-05-19T22:32:25Z)
• Line of Duty: Evaluating LLM Self-Knowledge via Consistency in Feasibility Boundaries [0.0]
  This study aims to obtain intrinsic insights into different types of LLM self-knowledge with a novel methodology.<n>We find that even frontier models like GPT-4o and Mistral Large are not sure of their own capabilities more than 80% of the time.
  arXiv  Detail & Related papers  (2025-03-14T10:07:07Z)
• LLM Internal States Reveal Hallucination Risk Faced With a Query [62.29558761326031]
  Humans have a self-awareness process that allows us to recognize what we don't know when faced with queries. This paper investigates whether Large Language Models can estimate their own hallucination risk before response generation. By a probing estimator, we leverage LLM self-assessment, achieving an average hallucination estimation accuracy of 84.32% at run time.
  arXiv  Detail & Related papers  (2024-07-03T17:08:52Z)
• Evaluating Large Language Models with Psychometrics [59.821829073478376]
  This paper offers a comprehensive benchmark for quantifying psychological constructs of Large Language Models (LLMs)<n>Our work identifies five key psychological constructs -- personality, values, emotional intelligence, theory of mind, and self-efficacy -- assessed through a suite of 13 datasets.<n>We uncover significant discrepancies between LLMs' self-reported traits and their response patterns in real-world scenarios, revealing complexities in their behaviors.
  arXiv  Detail & Related papers  (2024-06-25T16:09:08Z)
• Do Large Language Models Exhibit Cognitive Dissonance? Studying the Difference Between Revealed Beliefs and Stated Answers [13.644277507363036]
  We introduce Revealed Belief, an evaluation framework that evaluates Large Language Models (LLMs) on tasks requiring reasoning under uncertainty.<n>Our findings suggest that while LLMs frequently state the correct answer, their Revealed Belief shows that they often allocate probability mass inconsistently, exhibit systematic biases, and often fail to update their beliefs appropriately when presented with new evidence.
  arXiv  Detail & Related papers  (2024-06-21T08:56:35Z)
• Exploring the Cognitive Knowledge Structure of Large Language Models: An Educational Diagnostic Assessment Approach [50.125704610228254]
  Large Language Models (LLMs) have not only exhibited exceptional performance across various tasks, but also demonstrated sparks of intelligence. Recent studies have focused on assessing their capabilities on human exams and revealed their impressive competence in different domains. We conduct an evaluation using MoocRadar, a meticulously annotated human test dataset based on Bloom taxonomy.
  arXiv  Detail & Related papers  (2023-10-12T09:55:45Z)
• The Confidence-Competence Gap in Large Language Models: A Cognitive Study [3.757390057317548]
  Large Language Models (LLMs) have acquired ubiquitous attention for their performances across diverse domains. We exploit these models with diverse sets of questionnaires and real-world scenarios. Our findings reveal intriguing instances where models demonstrate high confidence even when they answer incorrectly.
  arXiv  Detail & Related papers  (2023-09-28T03:50:09Z)
• Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation [109.8527403904657]
  We show that large language models (LLMs) possess unwavering confidence in their knowledge and cannot handle the conflict between internal and external knowledge well. Retrieval augmentation proves to be an effective approach in enhancing LLMs' awareness of knowledge boundaries. We propose a simple method to dynamically utilize supporting documents with our judgement strategy.
  arXiv  Detail & Related papers  (2023-07-20T16:46:10Z)
• Revisiting the Reliability of Psychological Scales on Large Language Models [62.57981196992073]
  This study aims to determine the reliability of applying personality assessments to Large Language Models. Analysis of 2,500 settings per model, including GPT-3.5, GPT-4, Gemini-Pro, and LLaMA-3.1, reveals that various LLMs show consistency in responses to the Big Five Inventory.
  arXiv  Detail & Related papers  (2023-05-31T15:03:28Z)
• Do Large Language Models Know What They Don't Know? [74.65014158544011]
  Large language models (LLMs) have a wealth of knowledge that allows them to excel in various Natural Language Processing (NLP) tasks. Despite their vast knowledge, LLMs are still limited by the amount of information they can accommodate and comprehend. This study aims to evaluate LLMs' self-knowledge by assessing their ability to identify unanswerable or unknowable questions.
  arXiv  Detail & Related papers  (2023-05-29T15:30:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.