mlsanityData to 7 Oct 2026

Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challenges

arXiv 2409.02387 ↗First posted 4 Sep 2024cs.AI cs.CLcited by 48

Not on the map. Why?

Abstract (arXiv)

This comprehensive review explores the intersection of Large Language Models (LLMs) and cognitive science, examining similarities and differences between LLMs and human cognitive processes. We analyze methods for evaluating LLMs cognitive abilities and discuss their potential as cognitive models. The review covers applications of LLMs in various cognitive fields, highlighting insights gained for cognitive science research. We assess cognitive biases and limitations of LLMs, along with proposed methods for improving their performance. The integration of LLMs with cognitive architectures is examined, revealing promising avenues for enhancing artificial intelligence (AI) capabilities. Key challenges and future research directions are identified, emphasizing the need for continued refinement of LLMs to better align with human cognition. This review provides a balanced perspective on the current state and future potential of LLMs in advancing our understanding of both artificial and human intelligence.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 41 of its 80 references that are in the map. First posted on arXiv 4 Sep 2024.

Builds on

41 of 80 references.

References · 41

  1. 2022Using cognitive psychology to understand GPT-3cited by 389
  2. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 348
  3. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 288
  4. 2022Talking About Large Language Modelscited by 174
  5. 2022The Debate Over Understanding in AI's Large Language Modelscited by 142
  6. 2022Thinking Fast and Slow in Large Language Modelscited by 136
  7. 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thoughtcited by 118
  8. 2022Capturing Failures of Large Language Models via Human Cognitive Biasescited by 97
  9. 2022Shortcut Learning of Large Language Models in Natural Language Understandingcited by 83
  10. 2022Meaning without reference in large language modelscited by 76
  11. 2023Turning large language models into cognitive modelscited by 66
  12. 2024CogBench: a large language model walks into a psychology labcited by 60
29 more
  1. 2022Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning taskscited by 56
  2. 2023Large language models predict human sensory judgments across six modalitiescited by 47
  3. 2024Confabulation: The Surprising Value of Large Language Model Hallucinationscited by 42
  4. 2022Can language models handle recursively nested grammatical structures? A case study on comparing models and humanscited by 41
  5. 2023Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writerscited by 32
  6. 2024Contextual Feature Extraction Hierarchies Converge in Large Language Models and the Braincited by 32
  7. 2022Training language models to summarize narratives improves brain alignmentcited by 26
  8. 2024(Ir)rationality and Cognitive Biases in Large Language Modelscited by 23
  9. 2024Cognitive Personalized Search Integrating Large Language Models with an Efficient Memory Mechanismcited by 22
  10. 2023Challenging the appearance of machine intelligence: Cognitive bias in LLMs and Best Practices for Adoptioncited by 21
  11. 2023Exploiting Language Models as a Source of Knowledge for Cognitive Agentscited by 15
  12. 2022Psychologically-informed chain-of-thought prompts for metaphor understanding in large language modelscited by 14
  13. 2023Conceptual structure coheres in human cognition but not in large language modelscited by 14
  14. 2023Cognitive Effects in Large Language Modelscited by 14
  15. 2023Aspects of human memory and Large Language Modelscited by 12
  16. 2023Synergistic Integration of Large Language Models and Cognitive Architectures for Robust AI: An Exploratory Analysiscited by 11
  17. 2023Language Models are Bounded Pragmatic Speakers: Understanding RLHF from a Bayesian Cognitive Modeling Perspectivecited by 10
  18. 2023The Confidence-Competence Gap in Large Language Models: A Cognitive Studycited by 9
  19. 2024Memory, Consciousness and Large Language Modelcited by 9
  20. 2024Do Large Language Models Mirror Cognitive Language Processing?cited by 9
  21. 2024Bootstrapping Cognitive Agents with a Large Language Modelcited by 9
  22. 2024MulCogBench: A Multi-modal Cognitive Benchmark Dataset for Evaluating Chinese and English Computational Language Modelscited by 9
  23. 2023LLM Cognitive Judgements Differ From Humancited by 8
  24. 2021Language Models as a Knowledge Source for Cognitive Agentscited by 7
  25. 2024CogGPT: Unleashing the Power of Cognitive Dynamics on Large Language Modelscited by 6
  26. 2023On the Unexpected Abilities of Large Language Modelscited by 5
  27. 2022A Precis of Language Models are not Models of Languagecited by 4
  28. 2023Cognitive bias in large language models: Cautious optimism meets anti-Panglossian meliorismcited by 4
  29. 2024Modelling Language using Large Language Modelscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 27; 2026: 13.

48 papers.

Sort:

By area:

  1. 2024Jailbreaking and Mitigation of Vulnerabilities in Large Language Modelscited by 33
  2. 2024Surveying the MLLM Landscape: A Meta-Review of Current Surveyscited by 20
  3. 2024Large Language Model Benchmarks in Medical Taskscited by 16
  4. 2025Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversightcited by 15
  5. 2025Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendationscited by 10
  6. 2025Understanding LLM Scientific Reasoning through Promptings and Model's Explanation on the Answerscited by 10
  7. 2025Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Researchcited by 9
  8. 2025From Prompts to Constructs: A Dual-Validity Framework for Large Language Model Research in Psychologycited by 9
  9. 2024From Text to Multimodality: Exploring the Evolution and Impact of Large Language Models in Medical Practicecited by 8
  10. 2025A Comment On "The Illusion of Thinking": Reframing the Reasoning Cliff as an Agentic Gapcited by 8
  11. 2025How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patternscited by 8
  12. 2024A Comprehensive Guide to Explainable AI: From Classical Models to LLMscited by 7
36 more
  1. 2025The Achilles' Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilitiescited by 7
  2. 2024From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Modelscited by 6
  3. 2025GEAR: A General Evaluation Framework for Abductive Reasoningcited by 6
  4. 2025From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Modelscited by 5
  5. 2025From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detectioncited by 5
  6. 2025Adversarial Testing in LLMs: Insights into Decision-Making Vulnerabilitiescited by 3
  7. 2025THiNK: Can Large Language Models Think-aloud?cited by 3
  8. 2025Games Agents Play: Towards Transactional Analysis in LLM-based Multi-Agent Systemscited by 3
  9. 2025Adding LLMs to the psycholinguistic norming toolbox: A practical guide to getting the most out of human ratingscited by 3
  10. 2026Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teamingcited by 3
  11. 2025The potential -- and the pitfalls -- of using pre-trained language models as cognitive science theoriescited by 2
  12. 2025Not Minds, but Signs: Reframing LLMs through Semioticscited by 2
  13. 2025How Real Is AI Tutoring? Comparing Simulated and Human Dialogues in One-on-One Instructioncited by 2
  14. 2025Knowledge Transfer from Interaction Learningcited by 2
  15. 2026Discovering Differences in Strategic Behavior Between Humans and LLMscited by 2
  16. 2025Can an Easy-to-Hard Curriculum Make Reasoning Emerge in Small Language Models? Evidence from a Four-Stage Curriculum on GPT-2cited by 1
  17. 2025Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Modelscited by 1
  18. 2025TACLA: An LLM-Based Multi-Agent Tool for Transactional Analysis Training in Educationcited by 1
  19. 2025NL2CA: Auto-formalizing Cognitive Decision-Making from Natural Language Using an Unsupervised CriticNL2LTL Frameworkcited by 1
  20. 2026Heuristic Classification of Thoughts Prompting (HCoT): Integrating Expert System Heuristics for Structured Reasoning into Large Language Modelscited by 1
  21. 2024Rephrase and Contrast: Fine-Tuning Language Models for Enhanced Understanding of Communication and Computer Networkscited by 0
  22. 2024Deep Learning and Machine Learning, Advancing Big Data Analytics and Management: Object-Oriented Programmingcited by 0
  23. 2025Representation in large language modelscited by 0
  24. 2025Online Anti-sexist Speech: Identifying Resistance to Gender Bias in Political Discoursecited by 0
  25. 2025Is GPT-OSS All You Need? Benchmarking Large Language Models for Financial Intelligence and the Surprising Efficiency Paradoxcited by 0
  26. 2025Toward Agentic Environments: GenAI and the Convergence of AI, Sustainability, and Human-Centric Spacescited by 0
  27. 2026The Third Ambition: Artificial Intelligence and the Science of Human Behaviorcited by 0
  28. 2026A Retrieval-Augmented Language Assistant for Unmanned Aircraft Safety Assessment and Regulatory Compliancecited by 0
  29. 2026Analysis of the Neglect-Zero Effect in Large Language Modelscited by 0
  30. 2026Evaluating LLM Personalization via Semantic Constraint Verificationcited by 0
  31. 2026EVLA: An Electro-Aware Multimodal Assistant for Physically-Grounded Driving Reasoning and Controlcited by 0
  32. 2026A3M: Adaptive, Adversarial and Multi-Objective Learning for Strategic Bidding in Repeated Auctionscited by 0
  33. 2026Beyond Skepticism: Evaluating LLMs Pedagogical Intent Reasoning with the Adaptive Pedagogical Vigilance Frameworkcited by 0
  34. 2026FedCausal-Dyn: A Causal-Dynamic Paradigm for Federated Learning under Dynamic Feature Driftcited by 0
  35. 2026Graph-Based Modeling of Financial Volatility Dynamicscited by 0
  36. 2026AI Alignment through a Game-theoretic Lens: A Surveycited by 0