arXiv cs.AI· Haoran Ye, Tianrui Huo, Hangzhen Li, Xin Zhang, Guojie Song·· 10 小时前AI 评分49
Chiron:一个测量和预测人类行为的基础模型
A Foundation Model to Measure and Predict Human Behaviour
AI 导读
研究者推出基础模型 Chiron,通过联合微调 LLM 来表征心理构念、预测个体行为并让群体响应分布对齐人类统计数据。其训练与评估覆盖 36 个行为领域、78 个社会科学实验,含 288,307 条个人记录与 1,411,750 个原子行为决策。评估中 Chiron 预测个体行为比前沿 LLM 相对提升最高 28.4%,实验效应量估计误差降低 82.2%–94.3%。
正文 · 原文
Abstract: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. 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. 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). Together, these results establish Chiron as a unified computational instrument for measuring and predicting human behaviour.
| Comments: | 48 pages, 6 figures |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2611.24830 [cs.CL] |
| (or arXiv:2611.24830v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24830 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haoran Ye [view email]
[v1]
Wed, 18 Nov 2026 17:59:08 UTC (566 KB)
来源:arXiv cs.AI · arxiv.org