Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kitadai, Ayato, Fukasawa, Yusuke, Nishino, Nariaki
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918130635243520
author Kitadai, Ayato
Fukasawa, Yusuke
Nishino, Nariaki
author_facet Kitadai, Ayato
Fukasawa, Yusuke
Nishino, Nariaki
contents Large language models (LLMs) are increasingly used to simulate human decision-making, but their intrinsic biases often diverge from real human behavior--limiting their ability to reflect population-level diversity. We address this challenge with a persona-based approach that leverages individual-level behavioral data from behavioral economics to adjust model biases. Applying this method to the ultimatum game--a standard but difficult benchmark for LLMs--we observe improved alignment between simulated and empirical behavior, particularly on the responder side. While further refinement of trait representations is needed, our results demonstrate the promise of persona-conditioned LLMs for simulating human-like decision patterns at scale.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18600
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics
Kitadai, Ayato
Fukasawa, Yusuke
Nishino, Nariaki
Computer Science and Game Theory
Multiagent Systems
General Economics
Economics
Large language models (LLMs) are increasingly used to simulate human decision-making, but their intrinsic biases often diverge from real human behavior--limiting their ability to reflect population-level diversity. We address this challenge with a persona-based approach that leverages individual-level behavioral data from behavioral economics to adjust model biases. Applying this method to the ultimatum game--a standard but difficult benchmark for LLMs--we observe improved alignment between simulated and empirical behavior, particularly on the responder side. While further refinement of trait representations is needed, our results demonstrate the promise of persona-conditioned LLMs for simulating human-like decision patterns at scale.
title Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics
topic Computer Science and Game Theory
Multiagent Systems
General Economics
Economics
url https://arxiv.org/abs/2508.18600