# Centaur: a foundation model of human cognition

arXiv: https://arxiv.org/abs/2410.20268 · HTML: https://mlsanity.com/paper/2410.20268/

## Key facts

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

## Built on by (most cited first, 30 of 36)

- [LLM Social Simulations Are a Promising Research Method](https://mlsanity.com/paper/2504.02234/) (2025)
- [SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors](https://mlsanity.com/paper/2510.17516/) (2025)
- [Finetuning LLMs for Human Behavior Prediction in Social Science Experiments](https://mlsanity.com/paper/2509.05830/) (2025)
- [Generating Computational Cognitive Models using Large Language Models](https://mlsanity.com/paper/2502.00879/) (2025)
- [How Personality Traits Shape LLM Risk-Taking Behaviour](https://mlsanity.com/paper/2503.04735/) (2025)
- [Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions](https://mlsanity.com/paper/2505.11614/) (2025)
- [Be.FM: Open Foundation Models for Human Behavior](https://mlsanity.com/paper/2505.23058/) (2025)
- [Do Psychometric Tests Work for Large Language Models? Evaluation of Tests on Sexism, Racism, and Morality](https://mlsanity.com/paper/2510.11254/) (2025)
- [Aligning LLM with human travel choices: a persona-based embedding learning approach](https://mlsanity.com/paper/2505.19003/) (2025)
- [Whither symbols in the era of advanced neural networks?](https://mlsanity.com/paper/2508.05776/) (2025)
- [Using LLMs to Advance the Cognitive Science of Collectives](https://mlsanity.com/paper/2506.00052/) (2025)
- [CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models](https://mlsanity.com/paper/2512.07890/) (2025)
- [Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models](https://mlsanity.com/paper/2502.15678/) (2025)
- [Emergence of psychopathological computations in large language models](https://mlsanity.com/paper/2504.08016/) (2025)
- [Discovering Differences in Strategic Behavior Between Humans and LLMs](https://mlsanity.com/paper/2602.10324/) (2026)
- [The potential -- and the pitfalls -- of using pre-trained language models as cognitive science theories](https://mlsanity.com/paper/2501.12651/) (2025)
- [Cognitive maps are generative programs](https://mlsanity.com/paper/2504.20628/) (2025)
- [AI-enhanced semantic feature norms for 786 concepts](https://mlsanity.com/paper/2505.10718/) (2025)
- [AlignSurvey: A Comprehensive Benchmark for Human Preferences Alignment in Social Surveys](https://mlsanity.com/paper/2511.07871/) (2025)
- [Can Vision Language Models Learn Intuitive Physics from Interaction?](https://mlsanity.com/paper/2602.06033/) (2026)
- [Reasoning aligns language models to human cognition](https://mlsanity.com/paper/2602.08693/) (2026)
- [Automated scientific minimization of regret](https://mlsanity.com/paper/2505.17661/) (2025)
- [GTA: Generative Traffic Agents for Simulating Realistic Mobility Behavior](https://mlsanity.com/paper/2601.16778/) (2026)
- [BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks](https://mlsanity.com/paper/2606.24162/) (2026)
- [Understanding Task Representations in Neural Networks via Bayesian Ablation](https://mlsanity.com/paper/2505.13742/) (2025)
- [Towards Measurement Theory for Artificial Intelligence](https://mlsanity.com/paper/2507.05587/) (2025)
- [A Qualitative Comparative Evaluation of Cognitive and Generative Theories](https://mlsanity.com/paper/2510.03453/) (2025)
- [Informing AI Policy Assessment using Large-Scale Simulation of Interventions](https://mlsanity.com/paper/2605.27395/) (2026)
- [Architecture-Sensitive Supervised Fine-Tuning for Screen-Conditioned Action Prediction: A PiSAR Benchmark](https://mlsanity.com/paper/2605.29400/) (2026)
- [Posterior Twins: Distributional Behavioral Simulation for Enterprise Decisions](https://mlsanity.com/paper/2606.16415/) (2026)

## 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.