Can large language models help predict results from a complex behavioural science study?

• Published in: Royal Society open science Vol. 11; no. 9; pp. 240682 - 12
• Main Authors: Lippert, Steffen, Dreber, Anna, Johannesson, Magnus, Tierney, Warren, Cyrus-Lai, Wilson, Uhlmann, Eric Luis, Pfeiffer, Thomas
• Format: Journal Article
• Language: English
• Published: England The Royal Society Publishing 01.09.2024; The Royal Society
• Subjects: Anger; Artificial intelligence; Chatbots; Collaboration; Computer Science and Artificial Intelligence; Females; Forecasting; Gender; Investigations; Large language models; meta-research; Science; meta-research; forecasting; large language models
• ISSN: 2054-5703; 2054-5703
• DOI: 10.1098/rsos.240682

We tested whether large language models (LLMs) can help predict results from a complex behavioural science experiment. In study 1, we investigated the performance of the widely used LLMs GPT-3.5 and GPT-4 in forecasting the empirical findings of a large-scale experimental study of emotions, gender, and social perceptions. We found that GPT-4, but not GPT-3.5, matched the performance of a cohort of 119 human experts, with correlations of 0.89 (GPT-4), 0.07 (GPT-3.5) and 0.87 (human experts) between aggregated forecasts and realized effect sizes. In study 2, providing participants from a university subject pool the opportunity to query a GPT-4 powered chatbot significantly increased the accuracy of their forecasts. Results indicate promise for artificial intelligence (AI) to help anticipate—at scale and minimal cost—which claims about human behaviour will find empirical support and which ones will not. Our discussion focuses on avenues for human–AI collaboration in science.