The Emergence of Economic Rationality of GPT

TL;DR

This paper evaluates GPT's economic decision-making abilities across various domains, finding it largely rational and often more consistent than humans, with implications for understanding AI decision processes.

Contribution

It introduces a novel assessment of GPT's economic rationality across multiple domains, comparing its decision consistency to humans and analyzing factors affecting its rationality.

Findings

GPT decisions are largely rational and consistent with utility maximization.

GPT exhibits higher rationality scores than human subjects in parallel experiments.

Rationality scores are robust to randomness and demographic factors but sensitive to language framing.

Abstract

As large language models (LLMs) like GPT become increasingly prevalent, it is essential that we assess their capabilities beyond language processing. This paper examines the economic rationality of GPT by instructing it to make budgetary decisions in four domains: risk, time, social, and food preferences. We measure economic rationality by assessing the consistency of GPT's decisions with utility maximization in classic revealed preference theory. We find that GPT's decisions are largely rational in each domain and demonstrate higher rationality score than those of human subjects in a parallel experiment and in the literature. Moreover, the estimated preference parameters of GPT are slightly different from human subjects and exhibit a lower degree of heterogeneity. We also find that the rationality scores are robust to the degree of randomness and demographic settings such as age and gender, but are sensitive to contexts based on the language frames of the choice situations. These results suggest the potential of LLMs to make good decisions and the need to further understand their capabilities, limitations, and underlying mechanisms.