mlsanityData to 14 Oct 2026

Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests

arXiv 2310.20320 ↗First posted 31 Oct 2023cs.CL cs.AIcited by 48

Not on the map. Why?

Abstract (arXiv)

To what degree should we ascribe cognitive capacities to Large Language Models (LLMs), such as the ability to reason about intentions and beliefs known as Theory of Mind (ToM)? Here we add to this emerging debate by (i) testing 11 base- and instruction-tuned LLMs on capabilities relevant to ToM beyond the dominant false-belief paradigm, including non-literal language usage and recursive intentionality; (ii) using newly rewritten versions of standardized tests to gauge LLMs' robustness; (iii) prompting and scoring for open besides closed questions; and (iv) benchmarking LLM performance against that of children aged 7-10 on the same tasks. We find that instruction-tuned LLMs from the GPT family outperform other models, and often also children. Base-LLMs are mostly unable to solve ToM tasks, even with specialized prompting. We suggest that the interlinked evolution and development of language and ToM may help explain what instruction-tuning adds: rewarding cooperative communication that takes into account interlocutor and context. We conclude by arguing for a nuanced perspective on ToM in LLMs.

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). Builds on 28 of its 80 references that are in the map. First posted on arXiv 31 Oct 2023.

Builds on

28 of 80 references.

References · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2022Training language models to follow instructions with human feedbackcited by 15,971
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  8. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  9. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,984
  10. 2023LIMA: Less Is More for Alignmentcited by 1,100
  11. 2020A Primer in BERTology: What we know about how BERT workscited by 815
  12. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 763
16 more
  1. 2022Using cognitive psychology to understand GPT-3cited by 398
  2. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 292
  3. 2023How is ChatGPT's behavior changing over time?cited by 270
  4. 2023The False Promise of Imitating Proprietary LLMscited by 263
  5. 2023A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Modelscited by 246
  6. 2018Machine Theory of Mindcited by 226
  7. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  8. 2019Visualizing and Measuring the Geometry of BERTcited by 216
  9. 2023Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Modelscited by 163
  10. 2022Thinking Fast and Slow in Large Language Modelscited by 137
  11. 2023Turning large language models into cognitive modelscited by 67
  12. 2018Evaluating Theory of Mind in Question Answeringcited by 64
  13. 2023Boosting Theory-of-Mind Performance in Large Language Models via Promptingcited by 64
  14. 2023ToMChallenges: A Principle-Guided Dataset and Diverse Evaluation Tasks for Exploring Theory of Mindcited by 28
  15. 2023Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understandingcited by 20
  16. 2023MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logiccited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 10; 2025: 22; 2026: 15.

48 papers.

Sort:

By area:

  1. 2025Agentic Large Language Models, a surveycited by 108
  2. 2024ToMBench: Benchmarking Theory of Mind in Large Language Modelscited by 72
  3. 2024LLMs achieve adult human performance on higher-order theory of mind taskscited by 61
  4. 2023Instruction-tuning Aligns LLMs to the Human Braincited by 40
  5. 2025The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMscited by 36
  6. 2024A Comprehensive Evaluation of Cognitive Biases in LLMscited by 34
  7. 2024InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Contextcited by 26
  8. 2025Large Language Models Miss the Multi-Agent Markcited by 26
  9. 2025Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemmacited by 25
  10. 2025Theory of Mind in Large Language Models: Assessment and Enhancementcited by 25
  11. 2025Re-evaluating Theory of Mind evaluation in large language modelscited by 23
  12. 2024Evaluating Large Language Models with Psychometricscited by 22
36 more
  1. 2024Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Modelscited by 22
  2. 2026Large Language Model Reasoning Failurescited by 21
  3. 2026PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebracited by 12
  4. 2025Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applicationscited by 10
  5. 2025HARBOR: Exploring Persona Dynamics in Multi-Agent Competitioncited by 6
  6. 2024Multi-ToM: Evaluating Multilingual Theory of Mind Capabilities in Large Language Modelscited by 5
  7. 2025From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Modelscited by 5
  8. 2025The Thin Line Between Comprehension and Persuasion in LLMscited by 5
  9. 2025Investigating VLM Hallucination from a Cognitive Psychology Perspective: A First Step Toward Interpretation with Intriguing Observationscited by 4
  10. 2025Enhancing Conversational Agents with Theory of Mind: Aligning Beliefs, Desires, and Intentions for Human-Like Interactioncited by 3
  11. 2025Towards properly implementing Theory of Mind in AI systems: An account of four misconceptionscited by 3
  12. 2025Agents Require Metacognitive and Strategic Reasoning to Succeed in the Coming Labor Marketscited by 2
  13. 2026Beyond Words: Evaluating and Bridging Epistemic Divergence in User-Agent Interaction via Theory of Mindcited by 2
  14. 2026MafiaScope: Non-Invasive, Time-Resolved Belief Probing for LLM Agents in Social Deduction Gamescited by 2
  15. 2024Evaluating Theory of (an uncertain) Mind: Predicting the Uncertain Beliefs of Others in Conversation Forecastingcited by 1
  16. 2024Scaffolded Language Models with Language Supervision for Mixed-Autonomy: A Surveycited by 1
  17. 2025Metareasoning constraints couple narratives, affect and cognitioncited by 1
  18. 2025Contemplative Artificial Intelligencecited by 1
  19. 2025Can "consciousness" be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and Span Representation analysiscited by 1
  20. 2025Evaluating Contrast Localizer for Identifying Causal Units in Social & Mathematical Tasks in Language Modelscited by 1
  21. 2026GPT-4o Lacks Core Features of Theory of Mindcited by 1
  22. 2026A formal definition and meta-model for a machine theory of mindcited by 1
  23. 2026Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Actioncited by 1
  24. 2024Are Large Language Models Aligned with People's Social Intuitions for Human-Robot Interactions?cited by 0
  25. 2025Analyzing Cognitive Differences Among Large Language Models through the Lens of Social Worldviewcited by 0
  26. 2025Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Gamescited by 0
  27. 2025OnlineMate: An LLM-Based Multi-Agent Companion System for Cognitive Support in Online Learningcited by 0
  28. 2025Observer, Not Player: Simulating Theory of Mind in LLMs through Game Observationcited by 0
  29. 2026Theory Trace Card: Theory-Driven Socio-Cognitive Evaluation of LLMscited by 0
  30. 2026Are LLMs Smarter Than Chimpanzees? An Evaluation on Perspective Taking and Knowledge State Estimationcited by 0
  31. 2026Traces of Social Competence in Large Language Modelscited by 0
  32. 2026Persona Matters: Effects of Activation Steering on Short Answer Generation and Scoringcited by 0
  33. 2026Understanding Large Language Modelscited by 0
  34. 2026Evaluating Theory of Mind in Reasoning Models: Robustness over Reasoningcited by 0
  35. 2026The Mathematical Collective Unconscious: Jungian Archetypes within the Latent Spacecited by 0
  36. 2026Beyond Successful Play: Diagnosing Opponent Modeling in Large Language Modelscited by 0