Study: Grounding LLMs in Scientific Literature Rarely Improves Behavioral Predictions

duncanjwatts · x · 2026-08-01

In a recent academic presentation, researchers Robin Na, Duncan Watts, and Abdullah Almaatouq investigated whether grounding LLM predictions in scientific literature improves their ability to forecast behavioral experiments.

The study found that conditioning LLMs with scientific literature rarely improved prediction accuracy. This highlights the current limitations of LLMs when integrating rigorous academic knowledge to predict complex human behaviors.

Original post →

More from Research

Research channel →