[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-327341-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-327341-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","verifiable-knowledge-expansion-through-retrieval-grounded-formal-concept-analysis-research","Verifiable Knowledge Expansion through Retrieval-Grounded Formal Concept Analysis - Research","","Ontology construction requires deciding which objects, attributes, and structural relations are accepted as valid knowledge. Language models may propose such structures from text, but the proposed structures can be unsupported or inconsistent. This paper introduces a retrieval-augmented small language model framework that uses formal concept analysis as a symbolic verification loop. Starting from seed attributes, FCA generates implications over a growing context, while a retrieval-grounded oracle validates implications or provides counterexamples with incidence and consistency checks, enabling inspectable contradictions and corrections. Experiments on a rare ataxia setting report F1 ranges for evaluated and closure-based implications and analyze how seed size and ablations affect scores.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/verifiable-knowledge-expansion-through-retrieval-grounded-formal-concept-analysis-research/327341/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/verifiable-knowledge-expansion-through-retrieval-grounded-formal-concept-analysis-research/327341.png","ImageObject",300,407,{"name":42,"@type":43},"Emma Wilson","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-07","2026-09-21",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",5,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the paper address in ontology construction using language models?","Question",{"text":63,"@type":64},"It targets the risk that language-model outputs may be unsupported or inconsistent, so proposed knowledge must be verified before becoming a structural commitment.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does formal concept analysis (FCA) function in the proposed framework?",{"text":68,"@type":64},"FCA represents the current state as a formal context and tests implications, requiring counterexamples when an implication is invalid.",{"name":70,"@type":61,"acceptedAnswer":71},"What does the retrieval-grounded SLM oracle do during implication verification?",{"text":72,"@type":64},"It validates each FCA-generated implication or returns a counterexample, and it also supports incidence judgments, consistency checks, and attribute proposals.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},327341,1791403458,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,100,105,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":97,"show_sort_weight":98,"slug":99},"Comic",60,"comic",{"id":101,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},6,"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":55,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":111,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":117,"preview_page_count":4},3848291630094,"https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45","Verifiable Knowledge Expansion through Retrieval-Grounded  \nFormal Concept Analysis  \nYujin Yang  \n[yujinyang@hanyang.ac.kr](yujinyang@hanyang.ac.kr)[ ](yujinyang@hanyang.ac.kr)Hanyang University Seoul, Korea  \nHeejung Lee∗ [stdream@hanyang.ac.kr](stdream@hanyang.ac.kr)[ ](stdream@hanyang.ac.kr)Hanyang University Seoul, Korea  \narXiv :2607 .0 1773v 1 [ cs .AI] 2 Jul 2026  \nAbstract  \nOntology construction requires deciding which objects, attributes, and structural relations should be accepted as valid knowledge. Language models can propose such structures from text, but their outputs can still be unsupported or inconsistent. This paper proposesa retrieval-augmented small language model (SLM) framework that uses formal concept analysis (FCA) as a symbolic verification loop for knowledge expansion. Starting from seed attributes, FCA proposes implications over a growing formal context. A retrievalgrounded SLM oracle then validates each implication or returns a counterexample. The oracle also supports incidence judgments, consistency checks, and attribute proposals, making accepted implications, counterexamples, contradictions, and corrections inspectable. In a rare ataxia setting constructed from Orphadata resources, retrieval-grounded 10-seed runs obtain relation F1 of 0.29– 0.52 and closure-based implication F1 of 0.22–0.30 . Larger seed sets increase the number of evaluated implications and often improve implication F1 . The lower implication scores reflect a stricter evaluation of derived implications, where one missed or extra relation can affect several implication judgments. Ablations show that incidence judgments in a fixed object–attribute setting can improve closure-based implication scores. However, identifying positive object–attribute pairs remains difficult even when the candidate objects and attributes are fixed.  \nCCS Concepts  \n• Computing methodologies → Knowledge representation and reasoning; Natural language processing; • Information systems → Information retrieval; • Applied computing → Life and medical sciences.  \nKeywords  \nFormal concept analysis, Retrieval-augmented generation, Ontology construction, Small language models, Rare disease phenotyping  \nACM Reference Format:  \nYujin Yang and Heejung Lee. 2026. Verifiable Knowledge Expansion through Retrieval-Grounded Formal Concept Analysis. In Proceedings of the 8thepiDAMIK ACM SIGKDD Workshop on Data-driven Decision Making for  \n∗ Corresponding author.  \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 third-party components of this work must be honored.  \nFor all other uses, contact the owner/author(s) . epiDAMIK @ KDD’26, Jeju Island, Republic of Korea © 2026 Copyright held by the owner/author(s) .  \nPublic and Population Health, August 10, 2026, Jeju Island, Republic of Korea. ACM, New York, NY, USA, 8 pages.  \n1 Introduction  \nOntologies turn domain knowledge into a structure that can be shared, queried, checked, and reused [4, 6, 17] . In biomedical domains, for example, an ontology-like representation can connect rare disease objects to phenotype attributes and expose regularities among those phenotypes [7, 15] . However, building such structures manually is costly. Domain experts must inspect source documents, encode object–attribute relations, and revise the structure when new evidence reveals missing or inconsistent knowledge [1, 6, 17] . This makes ontology and knowledge graph construction a natural setting for language model assistance, but errors in domain specific knowledge make unverifiable generation risky [5, 11, 12]. The key technical challenge is therefore to verify proposed knowledge before it becomes a structural commitment. For example, the system may propose that a rare ataxia disease with Ata","cbCairKdAZDd2fgY","https://ap.wps.com/l/cbCairKdAZDd2fgY","pdf",1072781,"English","# Abstract\n# 1 Introduction\n# 2 Background","[{\"question\":\"What problem does the paper address in ontology construction using language models?\",\"answer\":\"It targets the risk that language-model outputs may be unsupported or inconsistent, so proposed knowledge must be verified before becoming a structural commitment.\"},{\"question\":\"How does formal concept analysis (FCA) function in the proposed framework?\",\"answer\":\"FCA represents the current state as a formal context and tests implications, requiring counterexamples when an implication is invalid.\"},{\"question\":\"What does the retrieval-grounded SLM oracle do during implication verification?\",\"answer\":\"It validates each FCA-generated implication or returns a counterexample, and it also supports incidence judgments, consistency checks, and attribute proposals.\"}]","Verifiable Knowledge Expansion through Retrieval-Grounded Formal Concept Analysis - Research | PDF",1789977021]