Nature paper finds LLMs match observed effects across 70 social science studies
RobbWiller · x · 2026-07-23
A new Nature paper asks whether LLMs can predict the outcomes of social science experiments.
Across 70 preregistered studies, the authors report a strong correspondence between LLM-predicted and observed effects, with a correlation of r = .85. The result suggests that LLMs can capture substantial regularities in social science experiments, at least in the settings tested here.
Related event: Nature Study: GPT-4 Can Predict Social Science Experiment Results(18 posts)→
More from Research
- Nature paper images cellular activity across all organs, revealing body-wide circuits — arjunrajlab · 2026-09-11
- SignNet 1M Dataset Released for Sign Language Research — ducha_aiki · 2026-09-11
- ECCV26 Oral: Flow Matching Enables Single-Stage Multi-View Point Cloud Registration — ducha_aiki · 2026-09-11
- InFlux++ Method Released — ducha_aiki · 2026-09-11
- Skyfall GS Uses Flux to Refine Gaussian Splatting, Accepted at ECCV 2026 — ducha_aiki · 2026-09-11
- Could 10k agents discover learning methods beyond backprop, or just tweak existing ones? — SeunghyunSEO7 · 2026-09-11