[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85577-en":3,"doc-seo-85577-105":30,"detail-sidebar-cat-0-en-105":92},{"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},85577,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Ideological Bias in LLMs Economic Causal Reasoning","Large language models can show systematic ideological bias when inferring economic causal effects, which matters as these models increasingly support policy analysis and economic reporting. The work extends the EconCausal benchmark with ideology-contested cases where intervention-oriented (progovernment) and market-oriented (pro-market) frameworks predict opposite causal signs. From 10,490 empirically verified causal triplets, 1,056 contested instances are used to evaluate 20 LLMs’ accuracy and error directionality.","arXiv :2604 .2 1334v2 [ cs .AI] 12 Jul 2026  \nIdeological Bias in LLMs’ Economic Causal Reasoning  \nDonggyu Lee1 Hyeok Yun2 Jungwon Kim2 Junsik Min3 Sungwon Park3 ∗ Sangyoon Park4 ∗ Jihee Kim2 ∗  \n1Graduate School of Data Science, KAIST, Daejeon, South Korea  \n2College of Business, KAIST, Daejeon, South Korea  \n3School of Computing, KAIST, Daejeon, South Korea  \n4Division of Social Science, HKUST, Hong Kong, China [donggyu.lee@kaist.ac.kr](donggyu.lee@kaist.ac.kr), ed [yun98@kaist.ac.kr](yun98@kaist.ac.kr),  \n[jungwonkim126@kaist.ac.kr](jungwonkim126@kaist.ac.kr), [junshik1211@kaist.ac.kr](junshik1211@kaist.ac.kr),  \n[psw0416@kaist.ac.kr](psw0416@kaist.ac.kr), [sangyoon@ust.hk](sangyoon@ust.hk), [jiheekim@kaist.ac.kr](jiheekim@kaist.ac.kr) ∗  \nAbstract  \nDo large language models (LLMs) exhibit systematic ideological bias when reasoning about economic causal effects? As LLMs are increasingly used in policy analysis and economic reporting, where directionally correct causal judgments are essential, this question has direct practical stakes. We present a systematic evaluation by extending the EconCausal benchmark with ideology-contested cases—instances where intervention-oriented (progovernment) and market-oriented (pro-market) perspectives predict divergent causal signs. From 10,490 causal triplets (treatment–outcome pairs with empirically verified effect directions) derived from top-tier economics and finance journals, we identify 1,056 ideology-contested instances and evaluate 20 state-of-the-art LLMs on their ability to predict empirically supported causal directions. We find that ideology-contested items are consistently harder than non-contested ones, and that across 18 of 20 models, accuracy is systematically higher when the empirically verified causal sign aligns with intervention-oriented expectations than with market-oriented ones. Moreover, when models err, their incorrect predictions disproportionately lean intervention-oriented—and this directional skew is not eliminated by one-shot in-context prompting. These results highlight that LLMs are not only less accurate on ideologically contested economic questions, but systematically less reliable in one ideological direction than the other, underscoring the need for direction-aware evaluation in high-stakes economic and policy settings.  \n1 Introduction  \nDo Large Language Models exhibit systematic ideological bias when reasoning about economic causal effects? This question is pressing because LLMs are increasingly deployed in high-stakes analytical workflows, such as economic reporting, policy evaluation, and corporate decision support (Kwon et al., 2024; Ludwig et al., 2025; Handler et al., 2024), where predicting causal directions correctly is essential. Yet in many such settings, that direction is genuinely contested: a single intervention can trigger competing mechanisms whose relative magnitudes are debated along ideological lines. A minimum wage increase, for instance, is expected to reduce hiring under a market-oriented framework that prioritizes labor cost effects, but to sustain employment under an intervention-oriented framework that emphasizes demand or job-matching gains. When LLMs predict causal directions in such settings, their outputs may implicitly privilege one set of priors over another, producing an invisible tilt in downstream policy advice.  \nExisting approaches to detecting such effects fall short in complementary ways. Work on LLM bias typically relies on survey-style instruments that probe expressed opinions or  \n∗∗ Co-corresponding authors.  \nFigure 1: Overview of ideological divergence in LLM economic causal reasoning  \npreferences, often in social or political domains, and does not assess how models reason about causal relationships grounded in empirical evidence. In contrast, benchmarks for causal reasoning focus on formal logic or context-dependent inference, but assume a single correct expectation for each causal effect and do not account ","cbCaijtG5XAU9gks","https://ap.wps.com/l/cbCaijtG5XAU9gks","pdf",946514,6,1,19,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What problem does the paper investigate about LLMs and economics?\",\"answer\":\"It examines whether LLMs exhibit systematic ideological bias when reasoning about economic causal effects, especially regarding the correct direction of causal signs.\"},{\"question\":\"How does the paper extend EconCausal for this evaluation?\",\"answer\":\"It adds ideology-contested cases where intervention-oriented and market-oriented frameworks predict divergent causal signs, then evaluates LLMs on their ability to match empirically verified causal directions.\"},{\"question\":\"What are the main findings about accuracy and error patterns across ideological directions?\",\"answer\":\"Ideology-contested items are consistently harder, and across 18 of 20 models accuracy is higher when the true causal sign aligns with intervention-oriented expectations; when models make mistakes, their errors skew toward intervention-oriented predictions and this skew is not removed by one-shot prompting.\"}]",1784204700,48,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"ideological-bias-in-llms-economic-causal-reasoning","",{"@graph":36,"@context":86},[37,54,69],{"@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":53},"https://docshare.wps.com/document/ideological-bias-in-llms-economic-causal-reasoning/85577/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the paper investigate about LLMs and economics?","Question",{"text":76,"@type":77},"It examines whether LLMs exhibit systematic ideological bias when reasoning about economic causal effects, especially regarding the correct direction of causal signs.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the paper extend EconCausal for this evaluation?",{"text":81,"@type":77},"It adds ideology-contested cases where intervention-oriented and market-oriented frameworks predict divergent causal signs, then evaluates LLMs on their ability to match empirically verified causal directions.",{"name":83,"@type":74,"acceptedAnswer":84},"What are the main findings about accuracy and error patterns across ideological directions?",{"text":85,"@type":77},"Ideology-contested items are consistently harder, and across 18 of 20 models accuracy is higher when the true causal sign aligns with intervention-oriented expectations; when models make mistakes, their errors skew toward intervention-oriented predictions and this skew is not removed by one-shot prompting.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},"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":22,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":107,"slug":137},"General","general"]