ICML 2025 paper: LLM social simulations are a promising research method
jacyanthis · x · 2026-10-08
Anthis links his ICML 2025 position paper (arXiv:2504.02234, with Brynjolfsson, Michael Bernstein et al.): LLM simulations of human subjects promise an accessible data source for behavioral research, but adoption is low. The paper identifies five tractable challenges—favoring context-rich prompting and fine-tuning on social science datasets—and argues simulations are already viable for pilot and exploratory studies. He also cites SimileAI building sim-specific models and John Horton's LLM-as-an-expert work at Expected Parrot.
More from Research
- Stanford's Anshul Kundaje Slams 'Universal Virtual Cell': Perturbation Prediction Is the Wrong Metric — anshulkundaje · 2026-10-08
- Kernaut: coding agents design Gaussian process kernels via program search — sirbayes · 2026-10-08
- Kernaut's discovered kernels stay interpretable: 16 scalar functions, inner-product form — sirbayes · 2026-10-08
- iOSWorld brings computer-use agent benchmarking to iOS at COLM 2026 — kohjingyu · 2026-10-08
- Epoch's InnovationEval: AI agents still far from producing real research innovations — Afinetheorem · 2026-10-08
- Dankrad: AI's inelegant math results reveal human bias from small context windows — CatAstro_Piyush · 2026-10-08