mlsanityData to 14 Oct 2026

A Review of Incorporating Psychological Theories in LLMs

arXiv 2505.00003 ↗First posted 28 Mar 2025cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Psychological insights have long shaped pivotal NLP breakthroughs, from attention mechanisms to reinforcement learning and social modeling. As Large Language Models (LLMs) develop, there is a rising consensus that psychology is essential for capturing human-like cognition, behavior, and interaction. This paper reviews how psychological theories can inform and enhance stages of LLM development. Our review integrates insights from six subfields of psychology, including cognitive, developmental, behavioral, social, personality psychology, and psycholinguistics. With stage-wise analysis, we highlight current trends and gaps in how psychological theories are applied. By examining both cross-domain connections and points of tension, we aim to bridge disciplinary divides and promote more thoughtful integration of psychology into NLP research.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 125 of its 317 references that are in the map. First posted on arXiv 28 Mar 2025.

Builds on

125 of 317 references.

References · 125

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  5. 2017Deep reinforcement learning from human preferencescited by 3,912
  6. 2020Learning to summarize from human feedbackcited by 2,588
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  8. 2016Concrete Problems in AI Safetycited by 1,642
  9. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
  10. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  11. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMscited by 573
  12. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 541
38 more
  1. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
  2. 2023Sentiment Analysis in the Era of Large Language Models: A Reality Checkcited by 268
  3. 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 266
  4. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 234
  5. 2023Evaluating Large Language Models in Theory of Mind Taskscited by 222
  6. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 222
  7. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  8. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  9. 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 207
  10. 2023FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactionscited by 171
  11. 2022Large Language Models with Controllable Working Memorycited by 169
  12. 2023Sources of Hallucination by Large Language Models on Inference Taskscited by 169
  13. 2024Quantifying the Persona Effect in LLM Simulationscited by 169
  14. 2023Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Modelscited by 163
  15. 2024Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learningcited by 155
  16. 2023Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHFcited by 133
  17. 2023Generative Language Models Exhibit Social Identity Biasescited by 111
  18. 2024SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationalescited by 105
  19. 2024Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planningcited by 97
  20. 2023Confronting Reward Model Overoptimization with Constrained RLHFcited by 96
  21. 2023Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Trackercited by 95
  22. 2024Group Robust Preference Optimization in Reward-free RLHFcited by 95
  23. 2023Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilitiescited by 89
  24. 2023Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinkingcited by 81
  25. 2024InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modelingcited by 79
  26. 2024PERSONA: A Reproducible Testbed for Pluralistic Alignmentcited by 73
  27. 2024Self-Contrast: Better Reflection Through Inconsistent Solving Perspectivescited by 71
  28. 2023Can ChatGPT Assess Human Personalities? A General Evaluation Frameworkcited by 70
  29. 2024Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometricscited by 59
  30. 2021ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mindcited by 58
  31. 2024BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Datacited by 50
  32. 2023CLASS: A Design Framework for building Intelligent Tutoring Systems based on Learning Science principlescited by 48
  33. 2023You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instrumentscited by 48
  34. 2023Personas as a Way to Model Truthfulness in Language Modelscited by 47
  35. 2023Exploring the psychology of LLMs' Moral and Legal Reasoningcited by 44
  36. 2022Long Document Summarization with Top-down and Bottom-up Inferencecited by 42
  37. 2023The History and Risks of Reinforcement Learning and Human Feedbackcited by 42
  38. 2023Self-Assessment Tests are Unreliable Measures of LLM Personalitycited by 39

50 most cited of 125 All 125 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMscited by 36
  2. 2026Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBenchcited by 1
  3. 2025ToMPO: Training LLM Strategic Decision Making from a Multi-Agent Perspectivecited by 0
  4. 2026Recursive Concept Evolution for Compositional Reasoning in Large Language Modelscited by 0
  5. 2026Empath: Tracing Multi-Level Emotion Dynamics in Crisis Counseling Dialoguescited by 0
  6. 2026Moral Combat: Exploiting Moral Foundations Theory to Jailbreak LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications
  2. 2024Open Models, Closed Minds? On Agents Capabilities in Mimicking Human Personalities through Open Large Language Models
  3. 2026Personality Expression Across Contexts: Linguistic and Behavioral Variation in LLM Agents
  4. 2025From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers
  5. 2026Evaluating LLMs as Human Surrogates in Controlled Experiments
  6. 2023Machine Psychology
  7. 2025Adding LLMs to the psycholinguistic norming toolbox: A practical guide to getting the most out of human ratings
  8. 2025Beyond BFI: The CSI for Enhanced Reliability and Validity in Evaluating LLM Personality Traits