Behavioral Economics of AI: LLM Biases and Corrections

64 Pages Posted: 15 Apr 2025

See all articles by Pietro Bini

Pietro Bini

Cornell University - SC Johnson Graduate School of Business

Lin William Cong

Cornell University - Samuel Curtis Johnson Graduate School of Management; Cornell SC Johnson College of Business; National Bureau of Economic Research (NBER)

Xing Huang

Washington University in St. Louis - Olin Business School

Lawrence J. Jin

SC Johnson College of Business, Cornell University; National Bureau of Economic Research (NBER)

Date Written: January 30, 2025

Abstract

Do generative AI models, as epitomized and popularized by large language models (LLMs), exhibit systematic behavioral biases in economic and financial decisions? If so, how can we mitigate these biases? Following the cognitive psychology literature and the experimental economics studies, we conduct the most comprehensive set of experiments to date---originally designed to document human biases---on prominent LLM families with variations in model version and scale. We document systematic patterns in the behavioral biases that LLMs exhibit. For experiments concerning the psychology of preferences, LLM responses become increasingly irrational and human-like as the models become more advanced or larger; however, for experiments concerning the psychology of beliefs, the most advanced large-scale models frequently generate rational responses. Further exploring various methods for correcting these behavioral biases reveals that prompting LLMs to make rational decisions according to the Expected Utility framework seems the most effective.

Keywords: AI, Behavioral Biases, Beliefs, Preferences, LLMs

JEL Classification: D03, G02, G11, G41

Suggested Citation

Bini, Pietro and Cong, Lin and Huang, Xing and Jin, Lawrence J., Behavioral Economics of AI: LLM Biases and Corrections (January 30, 2025). Available at SSRN: https://ssrn.com/abstract=5213130 or http://dx.doi.org/10.2139/ssrn.5213130

Pietro Bini

Cornell University - SC Johnson Graduate School of Business ( email )

Sage Hall
106 E Avenue
Ithaca, NY New York 14850
United States
607-375-7928 (Phone)

Lin Cong

Cornell University - Samuel Curtis Johnson Graduate School of Management ( email )

Ithaca, NY 14853
United States

HOME PAGE: http://www.linwilliamcong.com/

Cornell SC Johnson College of Business ( email )

Ithaca, NY 14850
United States

National Bureau of Economic Research (NBER) ( email )

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Xing Huang

Washington University in St. Louis - Olin Business School ( email )

Simon Hall 211
Washington University in St. Louis
St. Louis, MO 63130
United States

Lawrence J. Jin (Contact Author)

SC Johnson College of Business, Cornell University ( email )

310E Warren Hall
Ithaca, NY 14850
United States
607-255-0581 (Phone)

National Bureau of Economic Research (NBER) ( email )

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
219
Abstract Views
1,075
Rank
302,364
PlumX Metrics