mlsanityData to 14 Oct 2026

COKE: A Cognitive Knowledge Graph for Machine Theory of Mind

arXiv 2305.05390 ↗First posted 9 May 2023cs.CLcited by 27

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

Abstract (arXiv)

Theory of mind (ToM) refers to humans' ability to understand and infer the desires, beliefs, and intentions of others. The acquisition of ToM plays a key role in humans' social cognition and interpersonal relations. Though indispensable for social intelligence, ToM is still lacking for modern AI and NLP systems since they cannot access the human mental state and cognitive process beneath the training corpus. To empower AI systems with the ToM ability and narrow the gap between them and humans, in this paper, we propose COKE: the first cognitive knowledge graph for machine theory of mind. Specifically, COKE formalizes ToM as a collection of 45k+ manually verified cognitive chains that characterize human mental activities and subsequent behavioral/affective responses when facing specific social circumstances. In addition, we further generalize COKE using LLMs and build a powerful generation model COLM tailored for cognitive reasoning. Experimental results in both automatic and human evaluation demonstrate the high quality of COKE, the superior ToM ability of COLM, and its potential to significantly enhance social applications.

Key facts. Cited by 27 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 21 of its 54 references that are in the map. First posted on arXiv 9 May 2023.

Builds on

21 of 54 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs24 Oct
  2. 2020Language Models are Few-Shot Learners28 May

Other references · 19

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  6. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
  7. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 652
  8. 2020Recipes for building an open-domain chatbotcited by 593
  9. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  10. 2021Towards Emotional Support Dialog Systemscited by 299
  11. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  12. 2018Machine Theory of Mindcited by 226
7 more
  1. 2021GPT3Mix: Leveraging Large-scale Language Models for Text Augmentationcited by 187
  2. 2022SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualizationcited by 168
  3. 2020GLUCOSE: GeneraLized and COntextualized Story Explanationscited by 86
  4. 2021Towards Zero-Label Language Learningcited by 76
  5. 2022CICERO: A Dataset for Contextualized Commonsense Inference in Dialoguescited by 38
  6. 2022LAD: Language Models as Data for Zero-Shot Dialogcited by 18
  7. 2021IoT-Enabled Social Relationships Meet Artificial Social Intelligencecited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 7; 2025: 12; 2026: 6.

27 papers.

Sort:

By area:

  1. 2024Understanding World or Predicting Future? A Comprehensive Survey of World Modelscited by 166
  2. 2024OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Modelscited by 54
  3. 2023Towards A Holistic Landscape of Situated Theory of Mind in Large Language Modelscited by 32
  4. 2023ToMChallenges: A Principle-Guided Dataset and Diverse Evaluation Tasks for Exploring Theory of Mindcited by 28
  5. 2024InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Contextcited by 26
  6. 2024Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modelingcited by 25
  7. 2025Theory of Mind in Large Language Models: Assessment and Enhancementcited by 25
  8. 2025ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mindcited by 12
  9. 2024Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Modelscited by 8
  10. 2025The Essence of Contextual Understanding in Theory of Mind: A Study on Question Answering with Story Characterscited by 8
  11. 2025Persuasion Should be Double-Blind: A Multi-Domain Dialogue Dataset With Faithfulness Based on Causal Theory of Mindcited by 8
  12. 2025SocialSim: Towards Socialized Simulation of Emotional Support Conversationcited by 7
15 more
  1. 2025A Review of Incorporating Psychological Theories in LLMscited by 6
  2. 2026Graph World Models: Concepts, Taxonomy, and Future Directionscited by 6
  3. 2024The Future of Cognitive Strategy-enhanced Persuasive Dialogue Agents: New Perspectives and Trendscited by 4
  4. 2024Towards Reliable and Empathetic Depression-Diagnosis-Oriented Chatscited by 3
  5. 2025Explainable Depression Detection in Clinical Interviews with Personalized Retrieval-Augmented Generationcited by 3
  6. 2025Social Human Robot Embodied Conversation (SHREC) Dataset: Benchmarking Foundational Models' Social Reasoningcited by 2
  7. 2025CARE: Cognitive-reasoning Augmented Reinforcement for Emotional Support Conversationcited by 2
  8. 2025PolicyEvol-Agent: Evolving Policy via Environment Perception and Self-Awareness with Theory of Mindcited by 1
  9. 2025Are Large Language Models Effective Knowledge Graph Constructors?cited by 1
  10. 2025Integrating Machine Learning into Belief-Desire-Intention Agents: Current Advances and Open Challengescited by 1
  11. 2026Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluationscited by 1
  12. 2026A formal definition and meta-model for a machine theory of mindcited by 1
  13. 2026Are LLMs Smarter Than Chimpanzees? An Evaluation on Perspective Taking and Knowledge State Estimationcited by 0
  14. 2026When Cognitive Graphs Meet LLMs: BDEI Cognitive Pathways for Panic Emotional Arousal Predictioncited by 0
  15. 2026PerSo: Investigating Facets of LLMs' Social Intelligence in Real-World Persuasion Scenarioscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Understanding Social Reasoning in Language Models with Language Models
  2. 2024Multi-ToM: Evaluating Multilingual Theory of Mind Capabilities in Large Language Models
  3. 2023HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models
  4. 2024Probing the Robustness of Theory of Mind in Large Language Models
  5. 2025MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems
  6. 2024Language Models Represent Beliefs of Self and Others
  7. 2025Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?
  8. 2023Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models