Who is More Bayesian: Humans or ChatGPT?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mu, Tianshi, Rawat, Pranjal, Rust, John, Zhang, Chengjun, Zhong, Qixuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915243328798720
author Mu, Tianshi
Rawat, Pranjal
Rust, John
Zhang, Chengjun
Zhong, Qixuan
author_facet Mu, Tianshi
Rawat, Pranjal
Rust, John
Zhang, Chengjun
Zhong, Qixuan
contents We compare the performance of human and artificially intelligent (AI) decision makers in simple binary classification tasks where the optimal decision rule is given by Bayes Rule. We reanalyze choices of human subjects gathered from laboratory experiments conducted by El-Gamal and Grether and Holt and Smith. We confirm that while overall, Bayes Rule represents the single best model for predicting human choices, subjects are heterogeneous and a significant share of them make suboptimal choices that reflect judgement biases described by Kahneman and Tversky that include the ``representativeness heuristic'' (excessive weight on the evidence from the sample relative to the prior) and ``conservatism'' (excessive weight on the prior relative to the sample). We compare the performance of AI subjects gathered from recent versions of large language models (LLMs) including several versions of ChatGPT. These general-purpose generative AI chatbots are not specifically trained to do well in narrow decision making tasks, but are trained instead as ``language predictors'' using a large corpus of textual data from the web. We show that ChatGPT is also subject to biases that result in suboptimal decisions. However we document a rapid evolution in the performance of ChatGPT from sub-human performance for early versions (ChatGPT 3.5) to superhuman and nearly perfect Bayesian classifications in the latest versions (ChatGPT 4o).
format Preprint
id arxiv_https___arxiv_org_abs_2504_10636
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Who is More Bayesian: Humans or ChatGPT?
Mu, Tianshi
Rawat, Pranjal
Rust, John
Zhang, Chengjun
Zhong, Qixuan
General Economics
Economics
Artificial Intelligence
Methodology
We compare the performance of human and artificially intelligent (AI) decision makers in simple binary classification tasks where the optimal decision rule is given by Bayes Rule. We reanalyze choices of human subjects gathered from laboratory experiments conducted by El-Gamal and Grether and Holt and Smith. We confirm that while overall, Bayes Rule represents the single best model for predicting human choices, subjects are heterogeneous and a significant share of them make suboptimal choices that reflect judgement biases described by Kahneman and Tversky that include the ``representativeness heuristic'' (excessive weight on the evidence from the sample relative to the prior) and ``conservatism'' (excessive weight on the prior relative to the sample). We compare the performance of AI subjects gathered from recent versions of large language models (LLMs) including several versions of ChatGPT. These general-purpose generative AI chatbots are not specifically trained to do well in narrow decision making tasks, but are trained instead as ``language predictors'' using a large corpus of textual data from the web. We show that ChatGPT is also subject to biases that result in suboptimal decisions. However we document a rapid evolution in the performance of ChatGPT from sub-human performance for early versions (ChatGPT 3.5) to superhuman and nearly perfect Bayesian classifications in the latest versions (ChatGPT 4o).
title Who is More Bayesian: Humans or ChatGPT?
topic General Economics
Economics
Artificial Intelligence
Methodology
url https://arxiv.org/abs/2504.10636