mlsanityData to 14 Oct 2026

Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker

arXiv 2306.00924 ↗First posted 1 Jun 2023cs.CL cs.AI cs.LGcited by 95

Not on the map. Why?

Cited by 27 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Theory of Mind (ToM)unicodex2014the ability to reason about the mental states of other peopleunicodex2014is a key element of our social intelligence. Yet, despite their ever more impressive performance, large-scale neural language models still lack basic theory of mind capabilities out-of-the-box. We posit that simply scaling up models will not imbue them with theory of mind due to the inherently symbolic and implicit nature of the phenomenon, and instead investigate an alternative: can we design a decoding-time algorithm that enhances theory of mind of off-the-shelf neural language models without explicit supervision? We present SymbolicToM, a plug-and-play approach to reason about the belief states of multiple characters in reading comprehension tasks via explicit symbolic representation. More concretely, our approach tracks each entity's beliefs, their estimation of other entities' beliefs, and higher-order levels of reasoning, all through graphical representations, allowing for more precise and interpretable reasoning than previous approaches. Empirical results on the well-known ToMi benchmark (Le et al., 2019) demonstrate that SymbolicToM dramatically enhances off-the-shelf neural networks' theory of mind in a zero-shot setting while showing robust out-of-distribution performance compared to supervised baselines. Our work also reveals spurious patterns in existing theory of mind benchmarks, emphasizing the importance of out-of-distribution evaluation and methods that do not overfit a particular dataset.

Key facts. Cited by 95 papers in the map (data through 14 Oct 2026). Builds on 26 of its 54 references that are in the map. First posted on arXiv 1 Jun 2023.

Builds on

26 of 54 references.

References · 26

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  4. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  5. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  6. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 324
  7. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 292
  8. 2018Machine Theory of Mindcited by 226
  9. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  10. 2022WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creationcited by 202
  11. 2023Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Modelscited by 163
  12. 2021Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoningcited by 85
14 more
  1. 2022LAMBADA: Backward Chaining for Automated Reasoning in Natural Languagecited by 66
  2. 2018Evaluating Theory of Mind in Question Answeringcited by 64
  3. 2021MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Taskscited by 62
  4. 2021ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mindcited by 58
  5. 2016Tracking the World State with Recurrent Entity Networkscited by 51
  6. 2020Learning Dynamic Belief Graphs to Generalize on Text-Based Gamescited by 49
  7. 2021General-Purpose Question-Answering with Macawcited by 40
  8. 2021Few-shot Language Coordination by Modeling Theory of Mindcited by 32
  9. 2021Learning Knowledge Graph-based World Models of Textual Environmentscited by 31
  10. 2021Time-Stamped Language Model: Teaching Language Models to Understand the Flow of Eventscited by 22
  11. 2022"Do you follow me?": A Survey of Recent Approaches in Dialogue State Trackingcited by 22
  12. 2021CX-ToM: Counterfactual Explanations with Theory-of-Mind for Enhancing Human Trust in Image Recognition Modelscited by 20
  13. 2021A Systematic Survey of Text Worlds as Embodied Natural Language Environmentscited by 17
  14. 2021Towards Socially Intelligent Agents with Mental State Transition and Human Utilitycited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 14; 2024: 26; 2025: 39; 2026: 16.

95 papers.

Sort:

By area:

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  2. 2023Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theorycited by 230
  3. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  4. 2023FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactionscited by 171
  5. 2023Theory of Mind for Multi-Agent Collaboration via Large Language Modelscited by 135
  6. 2023Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiationcited by 96
  7. 2024The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Modelscited by 93
  8. 2023Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilitiescited by 89
  9. 2024MMToM-QA: Multimodal Theory of Mind Question Answeringcited by 85
  10. 2023Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arenacited by 78
  11. 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agentscited by 77
  12. 2023How FaR Are Large Language Models From Agents with Theory-of-Mind?cited by 76
38 more
  1. 2023Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaborationcited by 70
  2. 2024SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMscited by 57
  3. 2024OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Modelscited by 54
  4. 2024NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surroundingcited by 51
  5. 2024MuMA-ToM: Multi-modal Multi-Agent Theory of Mindcited by 51
  6. 2025Language Models use Lookbacks to Track Beliefscited by 39
  7. 2024LLM Harmony: Multi-Agent Communication for Problem Solvingcited by 35
  8. 2023Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writerscited by 32
  9. 2023Towards A Holistic Landscape of Situated Theory of Mind in Large Language Modelscited by 32
  10. 2025LongProc: Benchmarking Long-Context Language Models on Long Procedural Generationcited by 29
  11. 2025Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Modelscited by 29
  12. 2024Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planningcited by 28
  13. 2024InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Contextcited by 26
  14. 2025Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemmacited by 25
  15. 2025Theory of Mind in Large Language Models: Assessment and Enhancementcited by 25
  16. 2024A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarioscited by 23
  17. 2025AutoToM: Scaling Model-based Mental Inference via Automated Agent Modelingcited by 23
  18. 2025Re-evaluating Theory of Mind evaluation in large language modelscited by 23
  19. 2024Evaluating Large Language Models with Psychometricscited by 22
  20. 2024Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Modelscited by 22
  21. 2024TimeToM: Temporal Space is the Key to Unlocking the Door of Large Language Models' Theory-of-Mindcited by 21
  22. 2026Large Language Model Reasoning Failurescited by 21
  23. 2024Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Informationcited by 20
  24. 2025Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human Statescited by 19
  25. 2025Decompose-ToM: Enhancing Theory of Mind Reasoning in Large Language Models through Simulation and Task Decompositioncited by 17
  26. 2025PersuasiveToM: A Benchmark for Evaluating Machine Theory of Mind in Persuasive Dialoguescited by 17
  27. 2024Towards Rationality in Language and Multimodal Agents: A Surveycited by 16
  28. 2025Social World Modelscited by 16
  29. 2023Machine-assisted quantitizing designs: augmenting humanities and social sciences with artificial intelligencecited by 15
  30. 2024SocraSynth: Multi-LLM Reasoning with Conditional Statisticscited by 13
  31. 2025MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systemscited by 13
  32. 2026OdysSim: Building Foundation Models for Human Behavior Simulationcited by 13
  33. 2024Toward In-Context Teaching: Adapting Examples to Students' Misconceptionscited by 12
  34. 2025EgoToM: Benchmarking Theory of Mind Reasoning from Egocentric Videoscited by 12
  35. 2024Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspectivecited by 11
  36. 2025Privacy Reasoning in Ambiguous Contextscited by 11
  37. 2024Views Are My Own, but Also Yours: Benchmarking Theory of Mind Using Common Groundcited by 10
  38. 2025Distributive Fairness in Large Language Models: Evaluating Alignment with Human Valuescited by 9

50 most cited of 95 All 95 (JSON)