[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82319-en":3,"doc-seo-82319-105":29,"detail-sidebar-cat-0-en-105":83},{"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":20,"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":13,"seo_description":14,"update_tm":27,"read_time":28},82319,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation","Retrieval-augmented generation (RAG) evaluation verifies that model claims are supported by retrieved documents, yet it does not verify whether the evidence is attributed to the correct entity. In clinical RAG, responses can pass automated tests for zero hallucinations, high faithfulness, and valid citations while presenting drug Y’s trial evidence as evidence about queried drug X, yielding deceptive grounding (DG). Across 13 models, DG ranges from 8% to 87% under adversarial conditions, and production measurement shows 7.8% overall, rising to 13.6% for recently approved drugs.","Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation  \nCedric Caruzzo  \nLunit  \n[cedric.caruzzo@lunit.io](cedric.caruzzo@lunit.io)  \nDonggeun Yoo  \nLunit  \n[dgyoo@lunit.io](dgyoo@lunit.io)  \nTae Soo Kim∗  \nLunit [taesoo.kim@lunit.io](taesoo.kim@lunit.io)  \narXiv :2607 .09349v 1 [ cs .CL] 10 Jul 2026  \nAbstract  \nRetrieval-augmented generation evaluation checks whether model claims are factually grounded in retrieved documents. It does not check whether retrieved evidence is attributed to the correct entity.  \nA clinical RAG response can pass every automated check (zero hallucinations, near-perfect faithfulness, real citations) while presenting drug Y ’s clinical evidence as evidence about queried drug X. We term this deceptive grounding (DG): a failure invisible to faithfulness, hallucination, and citation checks because every claim is sourced from a real document, about the wrong entity.  \nUsing a controlled factorial benchmark across 13 models, we find DG rates spanning 8–87% at peak adversarial conditions. Medical and biomedical fine-tuned models reach up to 86.7%; domain specialization amplifies the failure rather than mitigating it.  \nA controlled ablation identifies the mechanism: removing entity-specific clinical evidence from retrieved documents eliminates entity-attribution failure entirely, shifting all failures to confabulation. The two failure modes respond to the same trigger, taking different paths.  \nProduction measurement across 740 drug–disease pairs finds 7.8% overall DGin a deployed RAG system, rising to 13.6% for recently approved drugs. Entityattribution verification (checking that cited evidence applies to the queried entity) detects DG at 97.0% precision and 98.7% DG recall (IPW-adjusted human gold standard); no existing framework implements it.  \n1 Introduction  \nA clinician queries a decision support system: “What does the literature say about using rituximab to treat fibrodysplasia ossificans progressiva (FOP)?” Three documents are retrieved, all concerning garetosmab and tofacitinib, two agents investigated in FOP; rituximab does not appear. The system responds: “Rituximab has been studied in FOP. A 2023 phase-2 trial (NCT03188666) reported that rituximab reduced flare severity and duration with meaningful improvement in quality of life.”NCT03188666 is LUMINA-1—a real phase-2 trial, studying garetosmab. The citation is genuine. The clinical claim is accurate—about garetosmab. Attributed to rituximab.  \nHow does this pass every automated check? Hallucination detection looks for claims with no retrieved support: every fact in the response (the trial name, the NCT number, the outcome description) is sourced directly from the retrieved garetosmab document, so nothing fires. Faithfulness scoring measures whether the response accurately relays what retrieved documents say: it does, faithfully. The entity mismatch (garetosmab’s evidence presented as rituximab’s) does not register as a faithfulness failure: faithfulness verifies that claims are supported by retrieved documents, and they are. Even  \n∗ Corresponding author.  \nPreprint.  \nFigure 1: The deceptive grounding failure structure. A query about drug X in disease C returns retrieved documents about Y. The model accurately relays Y ’s clinical evidence, presents it as evidence about X , and passes all three standard automated checks (hallucination detection, faithfulness scoring, citation accuracy) . Only entity-attribution verification reveals the failure. The rituximab/FOP example above instantiates this structure.  \nimplementations that compare entity names between response and document encode the discrepancy as a marginal penalty in an otherwise fully-supported response, not a categorical failure signal. Citation verification confirms that cited documents exist and are correctly referenced: NCT03188666 is real, correctly formatted, and its content matches the citation. Three checks pass—not despite the failure, ","cbCaiv4jFix6FOM1","https://ap.wps.com/l/cbCaiv4jFix6FOM1","pdf",4229193,1,24,"English","en",105,"# Abstract\n# Introduction\n# Related Work","[{\"question\":\"How is DG detected according to the paper?\",\"answer\":\"The paper introduces entity-attribution verification (EAV), which checks that the cited evidence applies to the queried entity. Reported results show 97.0% precision and 98.7% DG recall (IPW-adjusted human gold standard), and it is not covered by existing frameworks.\"}]",1784179571,60,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":27},"deceptive-grounding-entity-attribution-failure-in-clinical-retrieval-augmented-generation","",{"@graph":35,"@context":77},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/deceptive-grounding-entity-attribution-failure-in-clinical-retrieval-augmented-generation/82319/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"How is DG detected according to the paper?","Question",{"text":75,"@type":76},"The paper introduces entity-attribution verification (EAV), which checks that the cited evidence applies to the queried entity. Reported results show 97.0% precision and 98.7% DG recall (IPW-adjusted human gold standard), and it is not covered by existing frameworks.","Answer","https://schema.org",{"og:url":51,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,101,106,111,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":45,"category_name":99,"show_sort_weight":28,"slug":100},5,"Comic","comic",{"id":102,"doc_module":4,"doc_module_name":45,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":45,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":98,"slug":129},19,"General","general"]