[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-201222-105":59,"doc-detail-201222-en":122},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":115,"head_meta":117,"extra_data":119,"updated_unix":121},105,"en","to-rely-or-not-to-rely-evaluating-interventions-for-appropriate-reliance-on-large-language-models","To Rely or Not to Rely? Evaluating Interventions for Appropriate Reliance on Large Language Models","","Large Language Models increasingly shape decision-making, but users face a dual risk: over-relying on confident yet incorrect outputs or under-relying due to mistrust. This work benchmarks how well reliance interventions support appropriate reliance. Three interventions are tested via a randomized online experiment with 400 participants completing LSAT logical reasoning and image-based numerical estimation. After independent answers, participants receive modified LLM advice and answer again. Results show reductions in over-reliance without consistent gains in appropriate reliance, alongside poor calibration signals and confidence inflation after incorrect reliance decisions.",{"@graph":69,"@context":114},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/to-rely-or-not-to-rely-evaluating-interventions-for-appropriate-reliance-on-large-language-models/201222/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/to-rely-or-not-to-rely-evaluating-interventions-for-appropriate-reliance-on-large-language-models/201222.png","ImageObject",300,407,{"name":92,"@type":93},"Rhys","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-07","2026-09-04",true,{"@type":102,"interactionType":103,"userInteractionCount":46},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108],{"name":109,"@type":110,"acceptedAnswer":111},"How is the evaluation conducted and with what tasks?","Question",{"text":112,"@type":113},"A randomized online experiment with 400 participants tests two challenging tasks: LSAT logical reasoning and image-based numerical estimation. Participants answer once independently, then again after receiving LLM advice modified by one intervention.","Answer","https://schema.org",{"og:url":83,"og:type":116,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":118,"canonical":83},"index,follow",{"doc_id":120,"site_id":62},201222,1788528165,{"code":4,"msg":5,"data":123},{"doc_id":120,"user_id":124,"nickname":92,"user_avatar":125,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":126,"file_id":127,"file_url":128,"file_type":129,"file_size":130,"view_count":46,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":131,"language":132,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":133,"faqs":134,"seo_title":135,"seo_description":67,"update_tm":121,"read_time":26,"preview_page_count":4},687207024643,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","To Rely or Not to Rely? Evaluating Interventions for Appropriate Reliance on Large Language Models  \narXiv :2412 . 15584v3 [ cs .HC] 29 Oct 2025  \nJessica Y. Bo  \n[jbo@cs.toronto.edu](jbo@cs.toronto.edu)[ ](jbo@cs.toronto.edu)University of Toronto Toronto, Canada  \nSophia Wan  \n[sophia.wan@alumni.utoronto.ca](sophia.wan@alumni.utoronto.ca)[ ](sophia.wan@alumni.utoronto.ca)University of Toronto Toronto, Canada  \nAshton Anderson  \n[ashton@cs.toronto.edu](ashton@cs.toronto.edu)[ ](ashton@cs.toronto.edu)University of Toronto Toronto, Canada  \nFigure 1: LLM reliance interventions benchmarked: Reliance Disclaimer, Uncertainty Highlighting, and Implicit Answer.  \nAbstract  \nAs Large Language Models become integral to decision-making, optimism about their power is tempered with concern over their errors. Users may over-rely on LLM advice that is confidently stated but wrong, or under-rely due to mistrust. Reliance interventions have been developed to help users of LLMs, but they lack rigorous evaluation for appropriate reliance. We benchmark the performance of three relevant interventions by conducting a randomized online experiment with 400 participants attempting two challenging tasks: LSAT logical reasoning and image-based numerical estimation. For each question, participants first answered independently, then received LLM advice modified by one of three reliance interventions and answered the question again. Our findings indicate that while interventions reduce over-reliance, they generally fail to improve appropriate reliance. Furthermore, people became more confident after making incorrect reliance decisions in certain contexts, demonstrating poor calibration. Based on our findings, we discuss implications for designing effective reliance interventionsin human-LLM collaboration.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nCHI’25, April 26–May 01, 2025, Yokohama, Japan  \n© 2025 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 979-8-4007-1394-1/25/04  \n[https://doi.org/10.1145/3706598.3714097](https://doi.org/10.1145/3706598.3714097)  \nCCS Concepts  \n• Information systems → Information systems applications;  \n• Human-centered computing → Interaction design process and methods; Empirical studies in HCI.  \nKeywords  \nLarge Language Models, Human-LLM Collaboration, Appropriate Reliance, Over-reliance  \nACM Reference Format:  \nJessica Y. Bo, Sophia Wan, and Ashton Anderson. 2025. To Rely or Not to Rely? Evaluating Interventions for Appropriate Reliance on Large Language Models. In Proceedings of ACM Conference on Human Factors in Computing Systems (CHI’25), April 26–May 01, 2025, Yokohama, Japan. ACM, New York, NY, USA, 24 pages. [https://doi.org/10.1145/3706598.3714097](https://doi.org/10.1145/3706598.3714097)  \n1 Introduction  \nAs people increasingly incorporate Large Language Models (LLMs) into their decision-making workflows, there is cause for both tremendous optimism and skeptical concern [23, 92]. LLMs encode remarkably vast amounts of knowledge; can communicate with users in clear, natural language; and have the potential to improve both the quality and efficiency of users’ decision-making [75] . However, people can over-rely on LLM advice [33, 71, 73] or, in contrast, under-rely on it if they mistrust their LLM partner [89] . LLMs are prone to hallucination and error, yet often present their ou","cbCaiuvb3kRNXLn0","https://ap.wps.com/l/cbCaiuvb3kRNXLn0","pdf",5162174,24,"English","# Abstract\n# Introduction","[{\"question\":\"How is the evaluation conducted and with what tasks?\",\"answer\":\"A randomized online experiment with 400 participants tests two challenging tasks: LSAT logical reasoning and image-based numerical estimation. Participants answer once independently, then again after receiving LLM advice modified by one intervention.\"}]","To Rely or Not to Rely? Evaluating Interventions for Appropriate Reliance on Large Language Models | PDF"]