Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

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

Source

arXiv

arxiv.org/abs/2607.11632v1

Read the source

Source

Plain-Language Brief

Researchers investigate if large language models (LLMs) can reproduce human biases in decision-making, specifically in route choice, without explicitly specifying parameters for Cumulative Prospect Theory (CPT). Experiments show that LLMs can mimic non-rational human choices and behave consistently with prospect-theoretic effects under uncertainty. This suggests that AI models could be a scalable alternative for modeling human decision processes.

What the Document Says

  • Human choice behavior exhibits biases that deviate from full rationality.
  • Cumulative Prospect Theory (CPT) is an effective framework for characterizing such behavioral patterns.
  • Applying CPT at a large scale depends on specifying individual-level CPT parameters, which is challenging due to limitations in current methods.
  • Large language models (LLMs) are investigated as a possible solution to reproduce human biases in choice-making without explicitly specifying prospect-theoretic parameters.
  • Route choice was used as a representative scenario for the evaluation of LLM-generated decisions.
  • The experimental results show that LLMs can reproduce non-rational human choice biases and behave consistently with prospect-theoretic effects under uncertainty.
  • These findings suggest that AI models could offer a scalable alternative for modeling human decision processes.

Key Concepts Mentioned

  • human biases
  • route choice
  • Cumulative Prospect Theory (CPT)
  • large language models (LLMs)
  • decision-making

Claims Made by the Document

  • Human choice behavior deviates from full rationality.
  • LLMs can reproduce human biases in decision-making without explicitly specifying prospect-theoretic parameters.
  • LLMs can exhibit decision behaviors consistent with prospect-theoretic effects under uncertainty.

Evidence Used

  • Experimental results comparing LLM-generated decisions with established human behavioral patterns predicted by CPT

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.