[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124069-en":3,"doc-seo-124069-105":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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124069,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Impact of Fidelity and Robustness of Machine Learning Explanations on User Trust","Explainable machine learning (XAI/ML explanations) addresses the interpretability gap of opaque machine learning systems by revealing reasoning. This study examines how user trust responds to explanation fidelity and explanation robustness. A user study is conducted in a student performance prediction setting, comparing two scenarios: fidelity-based variations across explanation fidelity levels, and robustness-based variations across robustness levels. Trust is measured using self-reported trust and behaviour-based metrics, producing different conclusions across metrics and scenarios.","Impact of Fidelity and Robustness of Machine Learning Explanations on User Trust  \nBo Wang, Jianlong Zhou, Yiqiao Li, and Fang Chen  \nUniversity of Technology Sydney, Sydney, Australia [Bo.Wang-11@student.uts.edu.au](Bo.Wang-11@student.uts.edu.au)  \n[Jianlong.Zhou@uts.edu.au](Jianlong.Zhou@uts.edu.au)  \n[Yiqiao.Li-1@student.uts.edu.au](Yiqiao.Li-1@student.uts.edu.au)  \n[Fang.Chen@uts.edu.au](Fang.Chen@uts.edu.au)  \nAbstract. EXplainable machine learning (XML) has recently emerged as a promising approach to address the inherent opacity of machine learning (ML) systems by providing insights into their reasoning processes.  \nThis paper explores the relationships among user trust, fidelity, and robustness within the context of ML explanations. To investigate these relationships, a user study is implemented within the context of predicting students’ performance. The study is designed to focus on two scenarios: (1) fidelity-based scenario —exploring dynamics of user trust across different explanations at varying fidelity levels and (2) robustnessbased scenario—examining dynamics of in user trust concerning robustness. For each scenario, we conduct experiments based on two different metrics, including self-reported trust and behaviour-based trust metrics.  \nFor the fidelity-based scenario, we find that users trust both high and low-fidelity explanations compared to without-fidelity explanations (no explanations) based on the behaviour-based trust results, rather than relying on the self-reported trust results. We also obtain consistent findings based on different metrics, indicating no significant differences in user trust when comparing different explanations across fidelity levels. Additionally, for the robustness-based scenario, we get contrasting results from the two metrics. The self-reported trust metric does not demonstrate any variations in user trust concerning robustness levels, whereas the behaviour-based trust metric suggests that user trust tends to be higher when robustness levels are higher.  \nKeywords: Human computer interaction · Machine learning explanation · User trust · Fidelity · Robustness.  \n1 Introduction  \nMachine learning (ML) finds widespread applications in various domains, playing a pivotal role in numerous contexts. However, the lack of interpretability poses a significant challenge in understanding the inner workings of ML models. Hence, the explanation of machine learning holds the utmost importance. Explaining ML involves elucidating the intricate connections between input and outcome  \n2 B. Wang et al.  \nwithin ML models, facilitating user comprehension of the underlying reasoning. By elucidating the mechanisms of ML models, users can enhance their trust in the model’s decisions, gain interpretability of the results, and gain insights into the decision-making process [20] . Moreover, explaining machine learning provides researchers, developers, and decision-makers with opportunities to gain deeper insights and improve the models. Recently, the field of ML explanation has obtained considerable attention from researchers. For instance, in the domain of recommender system [18], image classifier [12], and medicine [7], the researchers demonstrate that users express deeper insights when provided with explanations than systems lacking explanatory capabilities.  \nFurthermore, the selection of appropriate ML explanation methods with superior performance hinges upon the quality of the explanations. The quality of ML explanations encompasses three crucial aspects: user-related factors (e.g. user trust and satisfaction), explanation-related factors ([e.g. fidelity](e.g. fidelity)), and modelrelated factors (e.g. robustness and fairness) [8] . User trust, as a critical aspect in ML explanations, represents one of the primary objectives in the explanatory process. It serves as a measurable criterion for quantifying subjective evaluation and enables assessing the quality of ML explanation methods. Further, fidelit","cbCaib1H6zWf4G6g","https://ap.wps.com/l/cbCaib1H6zWf4G6g","pdf",2786912,1,12,"English","en",105,"# Abstract\n## Research focus and scenarios\n## Metrics for measuring trust\n## Key findings","[{\"question\":\"What does the paper study about machine learning explanations?\",\"answer\":\"The paper investigates how user trust is influenced by the fidelity and robustness of machine learning explanations.\"},{\"question\":\"How is the user study designed in the paper?\",\"answer\":\"It uses a student performance prediction task and compares two scenarios: a fidelity-based scenario across different explanation fidelity levels, and a robustness-based scenario across different robustness levels.\"},{\"question\":\"Why do the results differ between self-reported and behaviour-based trust metrics?\",\"answer\":\"The paper reports that fidelity-related conclusions align with behaviour-based trust rather than self-reported trust, and that robustness-related conclusions can diverge: self-reported trust may show no changes while behaviour-based trust suggests higher trust for higher robustness.\"}]","Impact of Fidelity and Robustness of Machine Learning Explanations on User Trust | PDF",1785820179,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"impact-of-fidelity-and-robustness-of-machine-learning-explanations-on-user-trust","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"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/impact-of-fidelity-and-robustness-of-machine-learning-explanations-on-user-trust/124069/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What does the paper study about machine learning explanations?","Question",{"text":75,"@type":76},"The paper investigates how user trust is influenced by the fidelity and robustness of machine learning explanations.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the user study designed in the paper?",{"text":80,"@type":76},"It uses a student performance prediction task and compares two scenarios: a fidelity-based scenario across different explanation fidelity levels, and a robustness-based scenario across different robustness levels.",{"name":82,"@type":73,"acceptedAnswer":83},"Why do the results differ between self-reported and behaviour-based trust metrics?",{"text":84,"@type":76},"The paper reports that fidelity-related conclusions align with behaviour-based trust rather than self-reported trust, and that robustness-related conclusions can diverge: self-reported trust may show no changes while behaviour-based trust suggests higher trust for higher robustness.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"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":53,"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":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]