首页 > AI前沿 > A Foundation Model to Measure and Predict Human Behaviour

A Foundation Model to Measure and Predict Human Behaviour

arXiv自然语言 2026-11-19 01:59 20 阅读 查看原文

研究背景与模型提出

Large language models (LLMs) are increasingly used to infer psychological attributes, predict individual behaviour, and simulate human populations. However, despite generating plausible responses, they often misrepresent individuals and distort population statistics. Here we introduce Chiron, a foundation model to measure and predict human behaviour. We jointly fine-tune an LLM to represent psychological constructs, predict individual behaviour, and align population response distributions with human statistics.

训练与评估数据概况

The training and evaluation data span 36 behavioural domains and 78 social science experiments, comprising 288,307 person records, 1,411,750 atomic behavioural decisions, and 99,953 psychometric assessments over 109 psychological constructs.

评估结果

In our evaluations, Chiron's psychological measurements agree more closely with human self-reports and exhibit fewer biases that undermine psychometric validity. It predicts individual behaviour more accurately than frontier LLMs (up to 28.4% relative improvement). In simulations of social science experiments, it more accurately captures the direction and magnitude of human experimental effects (82.2--94.3% lower effect-size estimation error).

研究结论

Together, these results establish Chiron as a unified computational instrument for measuring and predicting human behaviour.