mlsanityData to 14 Oct 2026

Centaur: a foundation model of human cognition

arXiv 2410.20268 ↗First posted 26 Oct 2024cs.LGcited by 36

Not on the map. Why?

Abstract (arXiv)

Establishing a unified theory of cognition has been a major goal of psychology. While there have been previous attempts to instantiate such theories by building computational models, we currently do not have one model that captures the human mind in its entirety. A first step in this direction is to create a model that can predict human behavior in a wide range of settings. Here we introduce Centaur, a computational model that can predict and simulate human behavior in any experiment expressible in natural language. We derived Centaur by finetuning a state-of-the-art language model on a novel, large-scale data set called Psych-101. Psych-101 reaches an unprecedented scale, covering trial-by-trial data from over 60,000 participants performing over 10,000,000 choices in 160 experiments. Centaur not only captures the behavior of held-out participants better than existing cognitive models, but also generalizes to new cover stories, structural task modifications, and entirely new domains. Furthermore, we find that the model's internal representations become more aligned with human neural activity after finetuning. Taken together, our results demonstrate that it is possible to discover computational models that capture human behavior across a wide range of domains. We believe that such models provide tremendous potential for guiding the development of cognitive theories and present a case study to demonstrate this.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Oct 2024.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 22; 2026: 14.

36 papers.

Sort:

By area:

  1. 2025LLM Social Simulations Are a Promising Research Methodcited by 99
  2. 2025SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviorscited by 52
  3. 2025Finetuning LLMs for Human Behavior Prediction in Social Science Experimentscited by 39
  4. 2025Generating Computational Cognitive Models using Large Language Modelscited by 14
  5. 2025How Personality Traits Shape LLM Risk-Taking Behaviourcited by 9
  6. 2025Using Reinforcement Learning to Train Large Language Models to Explain Human Decisionscited by 9
  7. 2025Be.FM: Open Foundation Models for Human Behaviorcited by 9
  8. 2025Do Psychometric Tests Work for Large Language Models? Evaluation of Tests on Sexism, Racism, and Moralitycited by 9
  9. 2025Aligning LLM with human travel choices: a persona-based embedding learning approachcited by 7
  10. 2025Whither symbols in the era of advanced neural networks?cited by 7
  11. 2025Using LLMs to Advance the Cognitive Science of Collectivescited by 6
  12. 2025CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Modelscited by 5
24 more
  1. 2025Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Modelscited by 4
  2. 2025Emergence of psychopathological computations in large language modelscited by 4
  3. 2026Discovering Differences in Strategic Behavior Between Humans and LLMscited by 3
  4. 2025The potential -- and the pitfalls -- of using pre-trained language models as cognitive science theoriescited by 2
  5. 2025Cognitive maps are generative programscited by 2
  6. 2025AI-enhanced semantic feature norms for 786 conceptscited by 2
  7. 2025AlignSurvey: A Comprehensive Benchmark for Human Preferences Alignment in Social Surveyscited by 2
  8. 2026Can Vision Language Models Learn Intuitive Physics from Interaction?cited by 2
  9. 2026Reasoning aligns language models to human cognitioncited by 2
  10. 2025Automated scientific minimization of regretcited by 1
  11. 2026GTA: Generative Traffic Agents for Simulating Realistic Mobility Behaviorcited by 1
  12. 2026BehaviorBench: Benchmarking Foundation Models for Behavioral Science Taskscited by 1
  13. 2025Understanding Task Representations in Neural Networks via Bayesian Ablationcited by 0
  14. 2025Towards Measurement Theory for Artificial Intelligencecited by 0
  15. 2025A Qualitative Comparative Evaluation of Cognitive and Generative Theoriescited by 0
  16. 2026Informing AI Policy Assessment using Large-Scale Simulation of Interventionscited by 0
  17. 2026Architecture-Sensitive Supervised Fine-Tuning for Screen-Conditioned Action Prediction: A PiSAR Benchmarkcited by 0
  18. 2026Posterior Twins: Distributional Behavioral Simulation for Enterprise Decisionscited by 0
  19. 2026Mixture of Cognitive Experts in Large Vision-Language Modelscited by 0
  20. 2026Computational models of pragmatic reasoning with flexible generation of meaning and expression alternativescited by 0
  21. 2026Cognitive Convergence: Deep Similarities Between Large Language Models and Human Cognitioncited by 0
  22. 2026CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognitioncited by 0
  23. 2026AwarenessBench: Assessing Cognitive Capabilities of Language Modelscited by 0
  24. 2026Socio-Foundation: A Model for Generalizable Individual Behavior Simulation via Hierarchical Capability Distillationcited by 0