Saved in:
Bibliographic Details
Main Authors: Zhang, Runze, Zhang, Xiaowei, Zhao, Mingyang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.03310
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908574983127040
author Zhang, Runze
Zhang, Xiaowei
Zhao, Mingyang
author_facet Zhang, Runze
Zhang, Xiaowei
Zhao, Mingyang
contents LLMs are emerging tools for simulating human behavior in business, economics, and social science, offering a lower-cost complement to laboratory experiments, field studies, and surveys. This paper evaluates how well LLMs replicate human behavior in operations management. Using nine published experiments in behavioral operations, we assess two criteria: replication of hypothesis-test outcomes and distributional alignment via Wasserstein distance. LLMs reproduce most hypothesis-level effects, capturing key decision biases, but their response distributions diverge from human data, including for strong commercial models. We also test two lightweight interventions -- chain-of-thought prompting and hyperparameter tuning -- which reduce misalignment and can sometimes let smaller or open-source models match or surpass larger systems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_03310
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management
Zhang, Runze
Zhang, Xiaowei
Zhao, Mingyang
Machine Learning
Artificial Intelligence
LLMs are emerging tools for simulating human behavior in business, economics, and social science, offering a lower-cost complement to laboratory experiments, field studies, and surveys. This paper evaluates how well LLMs replicate human behavior in operations management. Using nine published experiments in behavioral operations, we assess two criteria: replication of hypothesis-test outcomes and distributional alignment via Wasserstein distance. LLMs reproduce most hypothesis-level effects, capturing key decision biases, but their response distributions diverge from human data, including for strong commercial models. We also test two lightweight interventions -- chain-of-thought prompting and hyperparameter tuning -- which reduce misalignment and can sometimes let smaller or open-source models match or surpass larger systems.
title Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.03310