Reproducing human biases in route choice using large language models: Toward scalable behavioral modeling

2026-07-13

AI Summary

This study addresses the challenge of accurately modeling irrational human preferences in large-scale route choice behavior, which is hindered by the difficulty of obtaining individual-level parameters for Cumulative Prospect Theory (CPT). The authors propose leveraging large language models (LLMs) to implicitly capture and reproduce systematic decision biases in human path selection without explicitly specifying CPT parameters. Through a behavioral experiment and a path simulation–based evaluation framework, they demonstrate that LLM-generated choices align closely with CPT predictions. This work provides the first evidence that LLMs can serve as a scalable, parameter-free tool for effectively simulating characteristic irrational decisions under uncertainty, offering a novel paradigm for large-scale agent-based behavioral modeling.

Abstract

Human choice behavior, including route choice, exhibits systematic behavioral biases that deviate from the assumptions of full rationality. Cumulative prospect theory (CPT) has been widely recognized as an effective framework for characterizing such behavioral patterns. However, its large-scale application, particularly in simulation and agent-based modeling, critically depends on specifying individual-level CPT parameters, which remain a major bottleneck. Conventional approaches typically rely on surveys and controlled experiments to calibrate CPT parameters, yet these methods are difficult to generalize and often fail to capture the full diversity of human decision-making. To address this challenge, this paper investigates whether large language models (LLMs) can reproduce human behavioral biases in choice-making without explicit specification of prospect-theoretic parameters. Using route choice as a representative scenario, we design a behavioral evaluation framework and systematically compare LLM-generated decisions with established human behavioral patterns predicted by CPT. Experimental results demonstrate that LLMs are capable of reproducing non-rational human choice biases and can exhibit decision behaviors consistent with prospect-theoretic effects under uncertainty. These findings suggest that generative AI models may provide a scalable alternative for modeling human decision processes and offer a promising foundation for next-generation large-scale agent-based simulation and AI-driven behavioral research.

Problem

• behavioral bias
• route choice
• cumulative prospect theory
• large-scale modeling
• human decision-making

Innovation

• large language models
• cumulative prospect theory
• behavioral bias
• route choice
• agent-based modeling