[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117562-en":3,"doc-seo-117562-105":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},117562,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Integrating human knowledge for explainable AI","This paper presents a methodology for integrating human expert knowledge into machine learning (ML) workflows to enhance both model interpretability and the quality of explanations from explainable AI (XAI). The approach upgrades standard ML and XAI pipelines by embedding domain knowledge at two stages: expert-guided data structuring and feature engineering during model development, and domain-aware synthetic neighborhoods during explanation generation. Visual analytics helps experts convert raw data into semantically richer representations. Validation through case studies on COVID-19 incidence prediction and vessel movement classification shows improved alignment with expert reasoning and higher-quality synthetic neighborhoods, while also discussing benefits and limitations.","City Research Online  \nCity, University of London Institutional Repository  \n\n| Citation: Cappuccio, E. , Kathirgamanathan, B. , Rinzivillo, S. , Andrienko, G. & Andrienko, N. (2025) . Integrating human knowledge for explainable AI. Machine Learning, 114(11), 250. doi: 10. 1007/s10994-025-06879-x\u003Cbr>This is the published version of the paper.\u003Cbr>This version of the publication may differ from the final published version. |\n| --- |\n| Permanent repository link: [https://openaccess.city.ac.uk/id/eprint/36171/](https://openaccess.city.ac.uk/id/eprint/36171/)\u003Cbr>Link to published version: [https://doi.org/10.1007/s10994-025-06879-x](https://doi.org/10.1007/s10994-025-06879-x)\u003Cbr>[Copyright:](Copyright: City Research Online aims to make research outputs of City)[ City Research Online aims to make research outputs of City](Copyright: City Research Online aims to make research outputs of City), University of London available to a wider audience. Copyright and Moral Rights remain with the author(s) and/or copyright holders. URLs from City Research Online may be freely distributed and linked to.\u003Cbr>Reuse: Copies of full items can be used for personal research or study, educational, or not-for-profit purposes without prior permission or charge. Provided that the authors, title and full bibliographic details are credited, a hyperlink and/or URL is given for the original metadata page and the content isnot changed in any way. |\n\n\n| City Research Online: | [http://openaccess.city.ac.uk/](http://openaccess.city.ac.uk/) | [publications@city.ac.uk](publications@city.ac.uk) |\n| --- | --- | --- |\n|  |  |  |\n\nIntegrating human knowledge for explainable AI  \nEleonora Cappuccio1 · Bahavathy Kathirgamanathan2 · Salvatore Rinzivillo1 · Gennady Andrienko2,3 · Natalia Andrienko2,3  \nReceived: 3 April 2025 / Revised: 7 July 2025 / Accepted: 25 August 2025 © The Author(s) 2025  \nAbstract  \nThis paper presents a methodology for integrating human expert knowledge into machine learning (ML) workflows to improve both model interpretability and the quality of explanations produced by explainable AI (XAI) techniques. We strive to enhance standard MLand XAI pipelines without modifying underlying algorithms, focusing instead on embedding domain knowledge at two stages: (1) during model development through expertguided data structuring and feature engineering, and (2) during explanation generation via domain-aware synthetic neighbourhoods. Visual analytics is used to support experts in transforming raw data into semantically richer representations. We validate the methodology in two case studies: predicting COVID-19 incidence and classifying vessel movement patterns. The studies demonstrated improved alignment of models with expert reasoning and better quality of synthetic neighbourhoods. We also explore using large language models (LLMs) to assist experts in developing domain-compliant data generators. Our findings highlight both the benefits and limitations of existing XAI methods and point toa research direction for addressing these gaps.  \nKeywords Knowledge-guided explainable AI (XAI) · Visual analytics · Trustworthy AI  \n1 Introduction  \nExplainable AI (XAI) systems often produce explanations that, while technically accurate, fail to align with domain experts’understanding and reasoning processes (Liao & Varshney, 2021; Abdul et al., 2018). This misalignment occurs because conventional machine learning (ML) and XAI approaches lack systematic mechanisms for incorporating domain expertise, relying instead solely on data-driven methods that often fail to capture meaningful domain concepts and relationships (von Rueden et al., 2023) .  \nWe hypothesize that systematic integration of domain knowledge can make ML models more understandable to humans by ensuring that both model behaviour and explanations  \nEditors: Riccardo Guidotti, Anna Monreale, Dino Pedreschi.  \nExtended author information available on the last page of the article  \n1 3  \nalign with expert ment","cbCaifaJBDBHthXR","https://ap.wps.com/l/cbCaifaJBDBHthXR","pdf",4223158,1,41,"English","en",105,"# Abstract\n# Introduction\n## Misalignment between XAI explanations and domain expertise\n## Research question and proposed framework\n## Expert-guided data structuring for ML pipelines\n## Domain-aware synthetic neighborhoods for XAI explanations","[{\"question\":\"How does the paper integrate human expert knowledge into ML models?\",\"answer\":\"It embeds domain knowledge at development time through expert-guided data structuring and feature engineering, producing structured representations before model training.\"},{\"question\":\"How does the method improve explanations generated by XAI techniques?\",\"answer\":\"It modifies neighborhood generation by creating domain-aware synthetic neighbors, so explanations remain realistic and logically consistent with domain constraints.\"},{\"question\":\"What evidence supports the proposed methodology?\",\"answer\":\"The paper validates it using two case studies: predicting COVID-19 incidence and classifying vessel movement patterns, showing improved alignment with expert reasoning and better synthetic neighborhood quality.\"}]","Integrating human knowledge for explainable AI | PDF",1785677021,103,{"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},"integrating-human-knowledge-for-explainable-ai","",{"@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/integrating-human-knowledge-for-explainable-ai/117562/",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","2026-08-02",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},"How does the paper integrate human expert knowledge into ML models?","Question",{"text":75,"@type":76},"It embeds domain knowledge at development time through expert-guided data structuring and feature engineering, producing structured representations before model training.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the method improve explanations generated by XAI techniques?",{"text":80,"@type":76},"It modifies neighborhood generation by creating domain-aware synthetic neighbors, so explanations remain realistic and logically consistent with domain constraints.",{"name":82,"@type":73,"acceptedAnswer":83},"What evidence supports the proposed methodology?",{"text":84,"@type":76},"The paper validates it using two case studies: predicting COVID-19 incidence and classifying vessel movement patterns, showing improved alignment with expert reasoning and better synthetic neighborhood quality.","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":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]