Entity · paper

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

paperactiveprovisionalreproducing-human-biases-in-route-choice-using-large-language-models-toward-scalable-behavioral-modeling-57357181·1 events·first seen 41h ago

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

Co-occurring entities

Cumulative Prospect Theory

More like this (12)

Automated reproducibility assessments in the social and behavioral sciences using large language models Understanding Large Language Models Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact Unintended Effects of Geographic Conditioning in Large Language Models Reasoning Language Models The Riddle Riddle: Testing Flexible Reasoning in Large Language Models and Humans Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play

Recent events (1)

5arXiv · cs.CL·41h ago·source ↗

LLMs reproduce human behavioral biases in route choice without explicit prospect-theoretic parameters

A new arXiv preprint investigates whether LLMs can replicate systematic human decision-making biases in route choice scenarios without explicitly specifying cumulative prospect theory (CPT) parameters. The authors design a behavioral evaluation framework and find that LLMs reproduce non-rational choice patterns consistent with CPT effects under uncertainty. The findings suggest LLMs could serve as a scalable substitute for survey-based parameter calibration in agent-based behavioral simulations, addressing a longstanding bottleneck in large-scale human decision modeling.

Agent and Tool Ecosystem Cumulative Prospect Theory Reproducing human biases in route choice using large language models: Toward scalable behavioral modeling