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

TY - JOUR

T1 - Can large language models help predict results from a complex behavioural science study?

AU - Lippert, Steffen

AU - Dreber, Anna

AU - Johannesson, Magnus

AU - Tierney, Warren

AU - Cyrus-Lai, Wilson

AU - Uhlmann, Eric Luis

AU - Emotion Expression Collaboration

AU - Elbæk, Christian T.

AU - Tønnesen, Mathilde Hedegaard

AU - Pfeiffer, Thomas

PY - 2024/9/25

Y1 - 2024/9/25

N2 - 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.

AB - 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.

KW - forecasting

KW - large language models

KW - meta-research

UR - http://www.scopus.com/inward/record.url?scp=85205290129&partnerID=8YFLogxK

U2 - 10.1098/rsos.240682

DO - 10.1098/rsos.240682

M3 - Journal article

C2 - 39323554

SN - 2054-5703

VL - 11

JO - Royal Society Open Science

JF - Royal Society Open Science

IS - 9

M1 - 240682

ER -