mlsanityData to 14 Oct 2026

Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities

arXiv 2311.10227 ↗First posted 16 Nov 2023cs.AI cs.CLcited by 89

On the map: World models → World models for language agents

also in 1 more
Abstract (arXiv)

Human interactions are deeply rooted in the interplay of thoughts, beliefs, and desires made possible by Theory of Mind (ToM): our cognitive ability to understand the mental states of ourselves and others. Although ToM may come naturally to us, emulating it presents a challenge to even the most advanced Large Language Models (LLMs). Recent improvements to LLMs' reasoning capabilities from simple yet effective prompting techniques such as Chain-of-Thought have seen limited applicability to ToM. In this paper, we turn to the prominent cognitive science theory "Simulation Theory" to bridge this gap. We introduce SimToM, a novel two-stage prompting framework inspired by Simulation Theory's notion of perspective-taking. To implement this idea on current ToM benchmarks, SimToM first filters context based on what the character in question knows before answering a question about their mental state. Our approach, which requires no additional training and minimal prompt-tuning, shows substantial improvement over existing methods, and our analysis reveals the importance of perspective-taking to Theory-of-Mind capabilities. Our findings suggest perspective-taking as a promising direction for future research into improving LLMs' ToM capabilities.

Key facts. Cited by 89 papers in the map (data through 14 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 15 of its 43 references that are in the map. First posted on arXiv 16 Nov 2023.

Builds on

15 of 43 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs24 Oct

Other references · 14

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  4. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  5. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  6. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  7. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 324
  8. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 292
  9. 2019Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoningcited by 285
  10. 2020Transformers as Soft Reasoners over Languagecited by 270
  11. 2023Understanding Social Reasoning in Language Models with Language Modelscited by 172
  12. 2023Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Modelscited by 163
2 more
  1. 2023Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Trackercited by 95
  2. 2021Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoningcited by 85

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 18; 2025: 43; 2026: 28.

89 papers.

Sort:

By area:

  1. 2024Understanding World or Predicting Future? A Comprehensive Survey of World Modelscited by 166
  2. 2024LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Modelscited by 99
  3. 2024MMToM-QA: Multimodal Theory of Mind Question Answeringcited by 85
  4. 2024ToMBench: Benchmarking Theory of Mind in Large Language Modelscited by 72
  5. 2024SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMscited by 57
  6. 2024OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Modelscited by 54
  7. 2024MuMA-ToM: Multi-modal Multi-Agent Theory of Mindcited by 51
  8. 2025Language Models use Lookbacks to Track Beliefscited by 39
  9. 2024Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoningcited by 33
  10. 2024Language Models Represent Beliefs of Self and Otherscited by 31
  11. 2024Meta Reasoning for Large Language Modelscited by 29
  12. 2025Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Modelscited by 29
38 more
  1. 2025Theory of Mind in Large Language Models: Assessment and Enhancementcited by 25
  2. 2025AutoToM: Scaling Model-based Mental Inference via Automated Agent Modelingcited by 23
  3. 2025Re-evaluating Theory of Mind evaluation in large language modelscited by 23
  4. 2024Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Modelscited by 22
  5. 2024TimeToM: Temporal Space is the Key to Unlocking the Door of Large Language Models' Theory-of-Mindcited by 21
  6. 2025Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human Statescited by 19
  7. 2025Decompose-ToM: Enhancing Theory of Mind Reasoning in Large Language Models through Simulation and Task Decompositioncited by 17
  8. 2025Social World Modelscited by 16
  9. 2025EgoToM: Benchmarking Theory of Mind Reasoning from Egocentric Videoscited by 12
  10. 2025ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mindcited by 12
  11. 2024Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Modelscited by 8
  12. 2025Persuasion Should be Double-Blind: A Multi-Domain Dialogue Dataset With Faithfulness Based on Causal Theory of Mindcited by 8
  13. 2025Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Languagecited by 8
  14. 2025Infusing Theory of Mind into Socially Intelligent LLM Agentscited by 8
  15. 2025Modeling Others' Minds as Codecited by 7
  16. 2025EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity Statescited by 6
  17. 2025POET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Image Generationcited by 6
  18. 2025A Review of Incorporating Psychological Theories in LLMscited by 6
  19. 2026RebuttalAgent: Strategic Persuasion in Academic Rebuttal via Theory of Mindcited by 6
  20. 2026PerspectiveGap: A Benchmark for Multi-Agent Orchestration Promptingcited by 6
  21. 2024Constrained Reasoning Chains for Enhancing Theory-of-Mind in Large Language Modelscited by 5
  22. 2024MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learningcited by 5
  23. 2024Multi-ToM: Evaluating Multilingual Theory of Mind Capabilities in Large Language Modelscited by 5
  24. 2025Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Riskscited by 5
  25. 2025Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Plannercited by 5
  26. 2025ToM-SSI: Evaluating Theory of Mind in Situated Social Interactionscited by 5
  27. 2025TactfulToM: Do LLMs Have the Theory of Mind Ability to Understand White Lies?cited by 5
  28. 2025HeaRT: A Hierarchical Circuit Reasoning Tree-Based Agentic Framework for AMS Design Optimizationcited by 5
  29. 2025MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agentscited by 5
  30. 2026ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinementcited by 5
  31. 2025Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planningcited by 4
  32. 2025Perspective Transition of Large Language Models for Solving Subjective Taskscited by 3
  33. 2025Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and Attitudescited by 3
  34. 2025UniToMBench: Integrating Perspective-Taking to Improve Theory of Mind in LLMscited by 3
  35. 2025Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategiescited by 3
  36. 2026SOTOPIA-TOM: Evaluating Privacy and Information Management in Multi-Agent Interaction with Theory of Mindcited by 3
  37. 2025Let's Put Ourselves in Sally's Shoes: Shoes-of-Others Prefilling Improves Theory of Mind in Large Language Modelscited by 2
  38. 2025PRISON: Unmasking the Criminal Potential of Large Language Modelscited by 2

50 most cited of 89 All 89 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models
  2. 2025On the Thinking-Language Modeling Gap in Large Language Models
  3. 2025Language Models Might Not Understand You: Evaluating Theory of Mind via Story Prompting
  4. 2025Do Large Language Models Have a Planning Theory of Mind? Evidence from MindGames: a Multi-Step Persuasion Task
  5. 2025XToM: Exploring the Multilingual Theory of Mind for Large Language Models
  6. 2025Doing Things with Words: Rethinking Theory of Mind Simulation in Large Language Models
  7. 2023MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logic
  8. 2024Mind Your Theory: Theory of Mind Goes Deeper Than Reasoning