[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86286-en":3,"doc-seo-86286-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86286,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Reproducing Human Biases in Route Choice Using Large Language Models: Toward Scalable Behavioral Modeling","Human choice behavior in route choice often shows systematic biases that deviate from full rationality assumptions. Cumulative prospect theory (CPT) provides a descriptive framework, but large-scale simulation and agent-based modeling require estimating CPT parameters from individual behavioral data, which is a major bottleneck. This work tests whether large language models can reproduce human choice biases without explicitly specifying prospect-theoretic parameters, comparing LLM outputs with CPT-predicted behavioral patterns.","arXiv :2607 . 1 1632v 1 [ cs .AI] 13 Jul 2026  \nReproducing human biases in route choice using large language models:  \nToward scalable behavioral modeling  \nJiangtao Hana,b , Shoufeng Maa,b , Shuxian Xua,b,∗, Geng Lia,b , Shuai Linga,b , Ning Jiaa,b , Zhengbing Hec,∗  \na Laboratory of Computation and Analytics of Complex Management Systems (CACMS), Tianjin University, China b College of Management and Economics, Tianjin University, China  \nc Faculty of Science and Engineering, University of Nottingham Ningbo China  \nAbstract  \nHuman 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 estimating CPT parameters based on individuallevel behavioral data, which remains a major bottleneck. Conventional approaches typically rely on surveysand 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.  \nKeywords: behavioral modeling, large language models, cumulative prospect theory, route choice, generative agent  \n∗ Corresponding author  \nEmail addresses: [shuxianxu@tju.edu.cn](shuxianxu@tju.edu.cn) (Shuxian Xu), [he.zb@hotmail.com](he.zb@hotmail.com) (Zhengbing He)  \n1. Introduction  \nIn real-world decision-making, individuals do not always behave in a fully rational and objective manner. Instead, decisions are often shaped by subjective perceptions, resulting in systematic behavioral biases that depart from the assumption of full rationality (Murphy and ten Brincke, 2018) . Route choice is a typical example of this phenomenon (Di et al., 2014) . For example, travelers usually make route choice decisions under varying traffic conditions, such as different travel times and congestion levels. Their decisions do not always follow the principle of minimizing travel cost or travel time, but instead exhibit characteristics that deviate from the predictions of fully rational choice models.  \nCumulative Prospect Theory (CPT) is arguably the most important and influential descriptive model ofrisky choice to date (Barberis, 2013, Fox et al., 2015, Murphy and ten Brincke, 2018) . Unlike classical expected utility theory, CPT can characterize key psychological mechanisms in human decision-making, including reference dependence, loss aversion, diminishing sensitivity, and nonlinear probability weighting. These mechanisms explain why individuals make asymmetric evaluations and exhibit different risk preferences under different gain and loss scenarios. Due to its strong behavioral explanatory power, CPT has been widely applied to various areas of travel behavior research, including mode choice (Zhou et al., 2024), departure time choice (Geng et al., 2023), parking mode choice (Hu et al., 2025), and electric vehicle charging mode choice (Zhang et al., 2026) .  \nHowever, the lar","cbCaiuxsJLrbnQWs","https://ap.wps.com/l/cbCaiuxsJLrbnQWs","pdf",4855446,4,1,34,"English","en",105,"# Introduction\n## Route choice and behavioral bias\n## Cumulative prospect theory (CPT)\n## Bottleneck of CPT parameter estimation\n## Motivation for large language models (LLMs)\n## Goal and evaluation approach","[{\"question\":\"What problem does the paper address in modeling route choice behavior?\",\"answer\":\"It targets the challenge that CPT-based behavioral modeling at scale depends on estimating CPT parameters from individual-level data, which is difficult and limits generalization.\"},{\"question\":\"How does the study evaluate whether LLMs can reproduce human biases?\",\"answer\":\"It uses route choice as a representative scenario, designs a behavioral evaluation framework, and systematically compares LLM-generated decisions with human behavioral patterns predicted by CPT.\"},{\"question\":\"What do the experimental results show about LLMs in uncertain decisions?\",\"answer\":\"The results indicate that LLMs can reproduce non-rational human choice biases and produce behaviors consistent with prospect-theoretic effects under uncertainty.\"}]",1784210069,86,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"reproducing-human-biases-in-route-choice-using-large-language-models-toward-scalable-behavioral-modeling","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/reproducing-human-biases-in-route-choice-using-large-language-models-toward-scalable-behavioral-modeling/86286/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-27","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in modeling route choice behavior?","Question",{"text":75,"@type":76},"It targets the challenge that CPT-based behavioral modeling at scale depends on estimating CPT parameters from individual-level data, which is difficult and limits generalization.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the study evaluate whether LLMs can reproduce human biases?",{"text":80,"@type":76},"It uses route choice as a representative scenario, designs a behavioral evaluation framework, and systematically compares LLM-generated decisions with human behavioral patterns predicted by CPT.",{"name":82,"@type":73,"acceptedAnswer":83},"What do the experimental results show about LLMs in uncertain decisions?",{"text":84,"@type":76},"The results indicate that LLMs can reproduce non-rational human choice biases and produce behaviors consistent with prospect-theoretic effects under uncertainty.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]