[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123045-en":3,"doc-seo-123045-105":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},123045,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","On the Relationship Between Interpretability and Explainability in Machine Learning","Interpretability and explainability have become central in machine learning because they support understanding and debugging predictors, especially in high-stakes domains. Despite serving related goals, literature often treats them as independent routes: explainability for complex black-box systems versus interpretable methods that disregard explainability tooling. This position paper argues they are not substitutes, identifies key shortcomings of each, and shows how considering both mitigates those drawbacks. It calls for a unified perspective and research targeting both areas simultaneously.","arXiv :2311 . 11491v2 [ cs .LG] 25 Apr 2024  \nOn the Relationship Between Interpretability and Explainability in Machine Learning  \nBenjamin Leblanc  \nUniversit´e Laval, Qu´ebec, Canada  \n[benjamin.leblanc.2@ulaval.ca](benjamin.leblanc.2@ulaval.ca)  \nAbstract. Interpretability and explainability have gained more and more attention in the field of machine learning as they are crucial when it comes to high-stakes decisions and troubleshooting. Since both provide information about predictors and their decision process, they are often seen as two independent means for one single end. This view has led to a dichotomous literature: explainability techniques designed for complex black-box models, or interpretable approaches ignoring the many explainability tools. In this position paper, we challenge the common idea that interpretability and explainability are substitutes for one another by listing their principal shortcomings and discussing how both of them mitigate the drawbacks of the other. In doing so, we call for a new perspective on interpretability and explainability, and works targeting both topics simultaneously, leveraging each of their respective assets.  \nKeywords: Interpretability · Explainability · Relationship · Definition.  \n1 Introduction  \nMachine learning (ML) is used in a variety of fields with numerous applications, such as image recognition [51], sentiment analysis [79], and language translation [21] . In some areas such as the medical field, ML-assisted predictions or decisions can drastically impact human life. For example, breast cancer [76] can be devastating if not diagnosed in time (or at all) . Still, many events made it clear that not understanding the inner workings and decision process of a predictor could lead to unfortunate events: job and loan applications biased toward men [17], mortgage-approval biased toward white applicants [68], higher credit card limits for men [102], etc. As pointed out by Goodman and Flaxman [36]: “If we do not know how ML [predictors] work, we cannot check or regulate them to ensure that they do not encode discrimination against minorities [...], we will not be able to learn from instances in which it is mistaken.”  \nTwo schools of thought seem to have emerged from this need for knowledge: either focusing on explaining black-boxes [81,39], or favoring interpretable predictors while completely discarding explainability [85] . Both approaches contain many flaws: interpretability can’t provide all that there is to know about a predictor [6], all the while being subjective [86], and interpretable predictors are, most of the time, harder to train than predictors in general [27] . On the other  \n2 B. Leblanc  \nhand, there is an obligation to trust the explanations [10] which, by definition, are necessarily wrong [73,85] and can provide more question than it answers [44] . As it is often understood that explainability reduces the need for interpretability, and vice versa, the literature on their practical application and the mitigation of their drawbacks is disjoint.  \nIn this work, we challenge the common belief that interpretability and explainability are substitutes for one another and argue that they actually are complementary, especially in that they mitigate the shortcomings of the other. Our first contribution is met by listing and discussing the principal drawbacks of explainability and interpretability raised in the literature. For our second contribution, we discuss how these limitations either disappear or diminish when considering both explained and interpretable predictors. Throughout the paper, we also show how both concepts differ in their very nature, thus necessarily aiming at different knowledge.  \nMany works critically discuss interpretability and its relationship with predictive performances [85] or with ML family of predictors [60], and its conceptual differences with explainability [60,86 ,56 ,50 , 19] . Yet, it is the first time, up to our knowledge, that a ","cbCaihLDKnKzMHFV","https://ap.wps.com/l/cbCaihLDKnKzMHFV","pdf",1024580,1,19,"English","en",105,"# Introduction\n## Two schools of thought\n# Defining and Discussing the Concepts at Hand\n## Core definitions and distinctions","[{\"question\":\"Why are interpretability and explainability important in machine learning?\",\"answer\":\"They help provide information about predictors and their decision process, which is crucial for troubleshooting and for high-stakes decisions.\"},{\"question\":\"What does the position paper claim about the relationship between interpretability and explainability?\",\"answer\":\"It challenges the idea that they are substitutes and argues they are complementary, with each mitigating the other’s shortcomings.\"},{\"question\":\"How does the paper handle differing definitions of key concepts?\",\"answer\":\"It emphasizes that many definitions exist for a single concept, so clearly defining the terms and paradigms used is necessary to avoid misunderstandings and enable idea transfer.\"}]","On the Relationship Between Interpretability and Explainability in Machine Learning | PDF",1785814371,48,{"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},"on-the-relationship-between-interpretability-and-explainability-in-machine-learning","",{"@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/on-the-relationship-between-interpretability-and-explainability-in-machine-learning/123045/",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},"Why are interpretability and explainability important in machine learning?","Question",{"text":75,"@type":76},"They help provide information about predictors and their decision process, which is crucial for troubleshooting and for high-stakes decisions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the position paper claim about the relationship between interpretability and explainability?",{"text":80,"@type":76},"It challenges the idea that they are substitutes and argues they are complementary, with each mitigating the other’s shortcomings.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the paper handle differing definitions of key concepts?",{"text":84,"@type":76},"It emphasizes that many definitions exist for a single concept, so clearly defining the terms and paradigms used is necessary to avoid misunderstandings and enable idea transfer.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":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":21,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]