[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-280411-105":59,"doc-detail-280411-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","isee-advancing-multi-shot-explainable-ai-using-case-based-recommendations-abstract","iSee - Advancing Multi-Shot Explainable AI Using Case-based Recommendations - Abstract","","Explainable AI (XAI) increases trust and satisfaction in AI-assisted decision-making, yet a single explainer often cannot satisfy the diverse or even individual needs of users. The iSee work proposes a “multi-shot” explanation strategy that combines multiple explainers into tailored explanation experiences for user groups. The iSee platform enables intelligent sharing and reuse of these experiences using case-based reasoning, supporting iterative design of explanation strategies via its iSee ontology. Mixed-methods evaluation with six design users confirms generalisable usability and utility and promotes adoption of XAI best practices.",{"@graph":69,"@context":123},[70,84,106],{"@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/isee-advancing-multi-shot-explainable-ai-using-case-based-recommendations-abstract/280411/",{"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/isee-advancing-multi-shot-explainable-ai-using-case-based-recommendations-abstract/280411.png","ImageObject",300,407,{"name":92,"@type":93},"Seraphina","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-22","2026-09-16",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why is a single explainer often insufficient in XAI systems?","Question",{"text":113,"@type":114},"A single explanation may not match the diverse needs of multiple users, and even individual users can require multiple explanations over time.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What is the iSee platform designed to provide?",{"text":118,"@type":114},"iSee is built to share and reuse “explanation experiences,” enabling design users to develop and iteratively revise multi-shot explanation strategies that meet end-user needs.",{"name":120,"@type":111,"acceptedAnswer":121},"How is the iSee platform evaluated in the paper?",{"text":122,"@type":114},"The study uses a summative mixed methods protocol to evaluate usability and utility with six design users across varying expertise levels in AI and XAI.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},280411,1789547882,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":130,"read_time":144,"preview_page_count":4},962075114101,"https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165","iSee: Advancing Multi-Shot Explainable AI Using Case-based Recommendations  \nAnjana Wijekoona, Nirmalie Wiratungaa, *, David Corsara, Kyle Martina, Ikechukwu Nkisi-Orjia, Chamath Palihawadanaa, Marta Caro-Martínezb, Belen Díaz-Agudob, Derek Bridgec and Anne Liretd  \naRobert Gordon University, Aberdeen, Scotland  \nb Universidad Complutense de Madrid, Spain  \ncUniversity College Cork, Ireland  \nd British Telecommunications, France  \narXiv :2408 . 12941v1 [ cs .AI] 23 Aug 2024  \nAbstract. Explainable AI (XAI) can greatly enhance user trust and satisfaction in AI-assisted decision-making processes. Recent findings suggest that a single explainer may not meet the diverse needs of multiple users in an AI system; indeed, even individual users may require multiple explanations. This highlights the necessity fora “multi-shot” approach, employing a combination of explainers to form what we introduce as an “explanation strategy”. Tailored to a specific user or a user group, an “explanation experience” describes interactions with personalised strategies designed to enhance their AI decision-making processes. The iSee platform is designed for the intelligent sharing and reuse of explanation experiences, using Casebased Reasoning to advance best practices in XAI. The platform provides tools that enable AI system designers, i.e. design users, to design and iteratively revise the most suitable explanation strategy for their AI system to satisfy end-user needs. All knowledge generated within the iSee platform is formalised by the iSee ontology for interoperability. We use a summative mixed methods study protocol to evaluate the usability and utility of the iSee platform with six design users across varying levels of AI and XAI expertise. Our findings confirm that the iSee platform effectively generalises across applications and its potential to promote the adoption of XAI best practices.  \n1 Introduction  \nXAI systems must be able to address a range of explanation needs (such as transparency, scrutability, and trust) and must do so in a manner that is relevant to a range of stakeholders. It is also now a regulatory requirement in many parts of the world such asthe right to obtain an explanation in the EU [8, 13] . It is essential for an AI system looking to implement XAI to learn from successful past experiences of XAI adaptations that reveal best practices. Case-based Reasoning (CBR) caters to this need whereby it learns from past experiences [2, 14] . The iSee platform has proposed utilising the CBR paradigm to capture knowledge and experience from successful adaptations of explainability within AI systems [37] .  \nIt is increasingly recognised that a single explanation is often insufficient to satisfy all situations and/or all stakeholders [3, 25] . Multi-shot explanations, allowing users to digest explanations from multiple algorithms over the course of a single interaction, have been demonstrated to provide more satisfactory user experiences [24, 37] .  \n∗ Corresponding Author. Email: [n.wiratunga@rgu.ac.uk](n.wiratunga@rgu.ac.uk)  \nFigure 1. iSee CBR Cycle  \nHowever, bespoke development of domain-specific and personalised explanation strategies is prohibitively expensive and requires significant domain and XAI expertise. Explainability toolkits have emerged to facilitate the development of explainability for use cases, including IBM-XAI 360 [4], Alibi [19] and Captum [20] . Where existing toolkits fall short, iSee fills this gap by providing support to design users, regardless of their level of expertise in XAI, to develop expla  \nnation strategies based on the collective experiences of others.  \nThe iSee Cockpit is designed to elicit stakeholder requirements for explainability from the design user, which drives the underpinning CBR paradigm of the platform. Accordingly, in this paper, we evaluate the iSee Cockpit tools for capturing these requirements from real-world design users towards the design of multi-shot explanation strategies. ","cbCailk2ulQ7vlN3","https://ap.wps.com/l/cbCailk2ulQ7vlN3","pdf",11385429,"English","# Introduction\n## Multi-shot explanations and explanation strategies\n## Related work\n# Related Work\n## Case-based reasoning and XAI links","[{\"question\":\"Why is a single explainer often insufficient in XAI systems?\",\"answer\":\"A single explanation may not match the diverse needs of multiple users, and even individual users can require multiple explanations over time.\"},{\"question\":\"What is the iSee platform designed to provide?\",\"answer\":\"iSee is built to share and reuse “explanation experiences,” enabling design users to develop and iteratively revise multi-shot explanation strategies that meet end-user needs.\"},{\"question\":\"How is the iSee platform evaluated in the paper?\",\"answer\":\"The study uses a summative mixed methods protocol to evaluate usability and utility with six design users across varying expertise levels in AI and XAI.\"}]","iSee - Advancing Multi-Shot Explainable AI Using Case-based Recommendations - Abstract | PDF",25]