Can LLMs Predict Experiment Results? Nature Paper Reveals Strong Alignment with Human Data

RobbWiller · x · 2026-07-23

A new paper published in Nature by Stanford researcher Robb Willer and collaborators explores whether Large Language Models (LLMs) can predict the outcomes of social science experiments.

The study finds a strong correspondence (r=0.85) between LLM-predicted effects and actually observed effects across 70 preregistered studies. This suggests significant potential for using LLMs as predictive tools in social science research.

Related event: Nature Study: GPT-4 Can Predict Social Science Experiment Results(15 posts)→

Original post →

More from Research

Research channel →