LLM forecasts were about 2x too large and weaker on field experiments
RobbWiller · x · 2026-07-23
This reply highlights the main limitations of the LLM forecasts.
- On average, LLM predictions were about 2x too large.
- Accuracy was weaker for small effects, stable pre-existing attitudes, field experiments, and non-text treatments.
- The authors conclude that LLM forecasts can inform research, but should not replace human evidence, especially in harder-to-predict domains.
Related event: Nature Study: GPT-4 Can Predict Social Science Experiment Results(18 posts)→
More from Research
- Datology webinar: Curation Studio matched top data baselines with under 20% compute — josh_wills · 2026-10-27
- KANLab: an interactive browser playground for Kolmogorov-Arnold Networks — Lukas Niehaus · 2026-10-27
- CMU's LLM2Cert synthesizes stability certificates verified via SMT and Lean — CarnegieMellonU · 2026-10-27
- NVIDIA open-sources FLORA, a robotics data engine ~125x cheaper than GPT-6 Astra — nvidia · 2026-10-27
- RSNA 2026 Deep Learning Labs return: eight hands-on AI classes over four days in Chicago — PRouzrokh · 2026-10-27
- Steering two orthogonal concept neurons makes a model compose "gnome" — Sauers_ · 2026-10-27