Selective Deficits in LLM Mental Self-Modeling in a Behavior-Based Test of Theory of Mind

• URL: http://arxiv.org/abs/2603.26089v1
• Date: Fri, 27 Mar 2026 05:41:30 GMT
• Title: Selective Deficits in LLM Mental Self-Modeling in a Behavior-Based Test of Theory of Mind
• Abstract summary: Theory of Mind is a human universal that enables us to navigate - and manipulate - the social world.<n>It is supported by our ability to form mental models of ourselves and others.<n>We develop an experimental paradigm that requires that subjects form representations of the mental states of themselves and others.
• Score: 2.538209532048867
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The ability to represent oneself and others as agents with knowledge, intentions, and belief states that guide their behavior - Theory of Mind - is a human universal that enables us to navigate - and manipulate - the social world. It is supported by our ability to form mental models of ourselves and others. Its ubiquity in human affairs entails that LLMs have seen innumerable examples of it in their training data and therefore may have learned to mimic it, but whether they have actually learned causal models that they can deploy in arbitrary settings is unclear. We therefore develop a novel experimental paradigm that requires that subjects form representations of the mental states of themselves and others and act on them strategically rather than merely describe them. We test a wide range of leading open and closed source LLMs released since 2024, as well as human subjects, on this paradigm. We find that 1) LLMs released before mid-2025 fail at all of our tasks, 2) more recent LLMs achieve human-level performance on modeling the cognitive states of others, and 3) even frontier LLMs fail at our self-modeling task - unless afforded a scratchpad in the form of a reasoning trace. We further demonstrate cognitive load effects on other-modeling tasks, offering suggestive evidence that LLMs are using something akin to limited-capacity working memory to hold these mental representations in mind during a single forward pass. Finally, we explore the mechanisms by which reasoning models succeed at the self- and other-modeling tasks, and show that they readily engage in strategic deception.

Related papers

• GPT-4o Lacks Core Features of Theory of Mind [0.09320657506524145]
  We use a cognitively-grounded definition of ToM to develop and test a new evaluation framework.<n>We find that even though LLMs succeed in approxing human judgments in a simple ToM paradigm, they fail at a logically equivalent task.
  arXiv  Detail & Related papers  (2026-02-12T16:33:58Z)
• The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context [48.70817145536136]
  StateLM is a new class of foundation models endowed with an internal reasoning loop to manage their own state.<n>By learning to dynamically engineering its own context, our model breaks free from the architectural prison of a fixed window.
  arXiv  Detail & Related papers  (2026-02-12T16:00:01Z)
• Multi-Agent Evolve: LLM Self-Improve through Co-evolution [53.00458074754831]
  Reinforcement Learning (RL) has demonstrated significant potential in enhancing the reasoning capabilities of large language models (LLMs)<n>Recent Self-Play RL methods, inspired by the success of the paradigm in games and Go, aim to enhance LLM reasoning capabilities without human-annotated data.<n>We propose Multi-Agent Evolve (MAE), a framework that enables LLMs to self-evolve in solving diverse tasks, including mathematics, reasoning, and general knowledge Q&A.
  arXiv  Detail & Related papers  (2025-10-27T17:58:02Z)
• Extreme Self-Preference in Language Models [0.30586855806896035]
  We found massive self-preferences in four widely used large language models (LLMs)<n>In word-association tasks, models overwhelmingly paired positive attributes with their own names, companies, and CEOs relative to those of their competitors.<n>We found that self-love consistently followed assigned, not true, identity.<n>This result raises questions about whether LLM behavior will be systematically influenced by self-preferential tendencies, including a bias toward their own operation and even their own existence.
  arXiv  Detail & Related papers  (2025-09-30T16:13:56Z)
• Artificial Phantasia: Evidence for Propositional Reasoning-Based Mental Imagery in Large Language Models [0.0]
  This study offers a novel approach for benchmarking complex cognitive behavior in artificial systems.<n>We created dozens of novel items of a classic mental imagery task from cognitive psychology.<n>We found that the best LLMs performed significantly above average human performance.
  arXiv  Detail & Related papers  (2025-09-27T04:36:12Z)
• Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts [79.1081247754018]
  Large Language Models (LLMs) are widely deployed in reasoning, planning, and decision-making tasks.<n>We propose a framework based on Contact Searching Questions(CSQ) to quantify the likelihood of deception.
  arXiv  Detail & Related papers  (2025-08-08T14:46:35Z)
• How Deep is Love in LLMs' Hearts? Exploring Semantic Size in Human-like Cognition [75.11808682808065]
  This study investigates whether large language models (LLMs) exhibit similar tendencies in understanding semantic size.<n>Our findings reveal that multi-modal training is crucial for LLMs to achieve more human-like understanding.<n> Lastly, we examine whether LLMs are influenced by attention-grabbing headlines with larger semantic sizes in a real-world web shopping scenario.
  arXiv  Detail & Related papers  (2025-03-01T03:35:56Z)
• A Survey on Self-Evolution of Large Language Models [116.54238664264928]
  Large language models (LLMs) have significantly advanced in various fields and intelligent agent applications. To address this issue, self-evolution approaches that enable LLMs to autonomously acquire, refine, and learn from experiences generated by the model itself are rapidly growing.
  arXiv  Detail & Related papers  (2024-04-22T17:43:23Z)
• LLM-driven Imitation of Subrational Behavior : Illusion or Reality? [3.2365468114603937]
  Existing work highlights the ability of Large Language Models to address complex reasoning tasks and mimic human communication. We propose to investigate the use of LLMs to generate synthetic human demonstrations, which are then used to learn subrational agent policies. We experimentally evaluate the ability of our framework to model sub-rationality through four simple scenarios.
  arXiv  Detail & Related papers  (2024-02-13T19:46:39Z)
• Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench [83.41621219298489]
  We evaluate Large Language Models' (LLMs) anthropomorphic capabilities using the emotion appraisal theory from psychology. We collect a dataset containing over 400 situations that have proven effective in eliciting the eight emotions central to our study. We conduct a human evaluation involving more than 1,200 subjects worldwide.
  arXiv  Detail & Related papers  (2023-08-07T15:18:30Z)
• Deception Abilities Emerged in Large Language Models [0.0]
  Large language models (LLMs) are currently at the forefront of intertwining artificial intelligence (AI) systems with human communication and everyday life. This study reveals that such strategies emerged in state-of-the-art LLMs, such as GPT-4, but were non-existent in earlier LLMs. We conduct a series of experiments showing that state-of-the-art LLMs are able to understand and induce false beliefs in other agents.
  arXiv  Detail & Related papers  (2023-07-31T09:27:01Z)
• 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)
• Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate [85.3444184685235]
  We propose a Multi-Agent Debate (MAD) framework, in which multiple agents express their arguments in the state of "tit for tat" and a judge manages the debate process to obtain a final solution. Our framework encourages divergent thinking in LLMs which would be helpful for tasks that require deep levels of contemplation.
  arXiv  Detail & Related papers  (2023-05-30T15:25:45Z)

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.