Saved in:
Bibliographic Details
Main Authors: Chen, Yaoyu, Hu, Yuheng, Lu, Yingda
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.01167
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915295425200128
author Chen, Yaoyu
Hu, Yuheng
Lu, Yingda
author_facet Chen, Yaoyu
Hu, Yuheng
Lu, Yingda
contents Large language models (LLMs) have demonstrated unprecedented emergent capabilities, including content generation, translation, and simulation of human behavior. Field experiments, on the other hand, are widely employed in social studies to examine real-world human behavior through carefully designed manipulations and treatments. However, field experiments are known to be expensive and time consuming. Therefore, an interesting question is whether and how LLMs can be utilized for field experiments. In this paper, we propose and evaluate an automated LLM-based framework to predict the outcomes of a field experiment. Applying this framework to 276 experiments about a wide range of human behaviors drawn from renowned economics literature yields a prediction accuracy of 78%. Moreover, we find that the distributions of the results are either bimodal or highly skewed. By investigating this abnormality further, we identify that field experiments related to complex social issues such as ethnicity, social norms, and ethical dilemmas can pose significant challenges to the prediction performance.
format Preprint
id arxiv_https___arxiv_org_abs_2504_01167
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Predicting Field Experiments with Large Language Models
Chen, Yaoyu
Hu, Yuheng
Lu, Yingda
Computers and Society
Large language models (LLMs) have demonstrated unprecedented emergent capabilities, including content generation, translation, and simulation of human behavior. Field experiments, on the other hand, are widely employed in social studies to examine real-world human behavior through carefully designed manipulations and treatments. However, field experiments are known to be expensive and time consuming. Therefore, an interesting question is whether and how LLMs can be utilized for field experiments. In this paper, we propose and evaluate an automated LLM-based framework to predict the outcomes of a field experiment. Applying this framework to 276 experiments about a wide range of human behaviors drawn from renowned economics literature yields a prediction accuracy of 78%. Moreover, we find that the distributions of the results are either bimodal or highly skewed. By investigating this abnormality further, we identify that field experiments related to complex social issues such as ethnicity, social norms, and ethical dilemmas can pose significant challenges to the prediction performance.
title Predicting Field Experiments with Large Language Models
topic Computers and Society
url https://arxiv.org/abs/2504.01167