Abstract
A foundation model fine-tuned from a large language model measures and predicts human behaviour and aligns simulated population responses with human statistics, improving accuracy over frontier LLMs.
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.
Community
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.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Benchmarking Psychological Dynamics in Generative Agents (2026)
- Enhancing LLMs with Cognitive-Affective Personality Inference for Simulating Human Social-Psychological Behavior (2026)
- Imperfectly Imperfect: Evaluating Graded Cognitive Diversity in LLM Persona Simulations (2026)
- Can Open-Weight Large Language Models (LLMs) Simulate Human Survey Populations? A Cross-Instrument Calibration Study (2026)
- Tracing Psychometric Inference in Large Language Models (2026)
- Learning to Simulate Individuals from Macro Social Signals (2026)
- Simulating Respondents, Not Single Questions: Coherent Survey Generation with Large Language Models (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2611.24830 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper