mlsanityData to 14 Oct 2026

Cognitive Convergence: Deep Similarities Between Large Language Models and Human Cognition

arXiv 2607.26179 ↗First posted 28 Jul 2026q-bio.NC cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

LLMs are widely regarded as alien intelligences, systems whose cognitive operations are fundamentally unlike our own. Apparent similarities to human cognition are therefore often seen as the result of anthropomorphic projection. We argue that this framing is mistaken. LLMs clearly differ from humans in important respects, including their physical substrate, learning history, and the environments with which they interact. These differences make it all the more striking that contemporary LLM-based systems converge with human cognition on a number of principles of cognitive organization with longstanding support in cognitive science. We identify structural correspondences across five dimensions: inferential organization, computational architecture, representational structure, prediction-driven learning, and reinforcement-learning-like mechanisms supporting goal-directed action. These correspondences support a broader model of intelligent cognition in which core principles long used to explain human intelligence also characterize contemporary LLM-based systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 64 of its 163 references that are in the map. First posted on arXiv 28 Jul 2026.

Builds on

64 of 163 references.

References · 64

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2022Training language models to follow instructions with human feedbackcited by 15,971
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  7. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  9. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  10. 2019Language Models as Knowledge Bases?cited by 1,936
  11. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  12. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,336
38 more
  1. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  2. 2022Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 smallcited by 1,165
  3. 2022In-context Learning and Induction Headscited by 964
  4. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 938
  5. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  6. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 719
  7. 2022What Can Transformers Learn In-Context? A Case Study of Simple Function Classescited by 715
  8. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 557
  9. 2022Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Spacecited by 532
  10. 2026Kimi K2.5: Visual Agentic Intelligencecited by 501
  11. 2024Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Modelscited by 435
  12. 2023Cognitive Architectures for Language Agentscited by 429
  13. 2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 422
  14. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 407
  15. 2022Using cognitive psychology to understand GPT-3cited by 398
  16. 2025Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscationcited by 384
  17. 2025Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domainscited by 366
  18. 2023Role-Play with Large Language Modelscited by 294
  19. 2025DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoningcited by 280
  20. 2022Emergent Analogical Reasoning in Large Language Modelscited by 240
  21. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 237
  22. 2023Evaluating Large Language Models in Theory of Mind Taskscited by 222
  23. 2019Commonsense Knowledge Mining from Pretrained Modelscited by 189
  24. 2022Talking About Large Language Modelscited by 175
  25. 2023Getting aligned on representational alignmentcited by 143
  26. 2022Analyzing Transformers in Embedding Spacecited by 132
  27. 2023How do Language Models Bind Entities in Context?cited by 108
  28. 2023Language Models Implement Simple Word2Vec-style Vector Arithmeticcited by 98
  29. 2025Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corporacited by 88
  30. 2024Understanding the Limits of Vision Language Models Through the Lens of the Binding Problemcited by 75
  31. 2021Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Predictioncited by 59
  32. 2025Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languagescited by 59
  33. 2025How Linguistics Learned to Stop Worrying and Love the Language Modelscited by 51
  34. 2025Emergent Hierarchical Reasoning in LLMs through Reinforcement Learningcited by 42
  35. 2022Can language models handle recursively nested grammatical structures? A case study on comparing models and humanscited by 41
  36. 2024Why Do Large Language Models (LLMs) Struggle to Count Letters?cited by 38
  37. 2024Centaur: a foundation model of human cognitioncited by 36
  38. 2023Do large language models resemble humans in language use?cited by 34

50 most cited of 64 All 64 (JSON)

Built on by

Not cited yet.