{"id":"https://openalex.org/W7154347880","doi":"https://doi.org/10.48550/arxiv.2604.10389","title":"BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection","display_name":"BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7154347880","doi":"https://doi.org/10.48550/arxiv.2604.10389"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.10389","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10389","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.10389","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133615692","display_name":"Saukun Thika You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You, Saukun Thika","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133577480","display_name":"Nguyen Anh Khoa Tran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tran, Nguyen Anh Khoa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133604374","display_name":"Wesley K. Marizane","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marizane, Wesley K.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030145378","display_name":"Hanshu Rao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rao, Hanshu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133607102","display_name":"Qiunan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qiunan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027237221","display_name":"Xiaolei Huang","orcid":"https://orcid.org/0000-0003-0478-8715"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Xiaolei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.47369998693466187,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.47369998693466187,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.4505999982357025,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.010400000028312206,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.6456000208854675},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5012000203132629},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48739999532699585},{"id":"https://openalex.org/keywords/substitution","display_name":"Substitution (logic)","score":0.4429999887943268},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.4171999990940094},{"id":"https://openalex.org/keywords/snomed-ct","display_name":"SNOMED CT","score":0.3785000145435333},{"id":"https://openalex.org/keywords/adjudication","display_name":"Adjudication","score":0.3249000012874603}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6815999746322632},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.6456000208854675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5626000165939331},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5012000203132629},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48739999532699585},{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4016999900341034},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3986999988555908},{"id":"https://openalex.org/C206497026","wikidata":"https://www.wikidata.org/wiki/Q1753883","display_name":"SNOMED CT","level":3,"score":0.3785000145435333},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32989999651908875},{"id":"https://openalex.org/C204434341","wikidata":"https://www.wikidata.org/wiki/Q357789","display_name":"Adjudication","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.26750001311302185}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.10389","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10389","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.10389","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10389","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4973832964897156}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Terminology":[0],"substitution":[1,116],"errors":[2],"in":[3,28],"clinical":[4,51,57,114,190],"notes,":[5],"where":[6],"one":[7],"medical":[8],"term":[9],"is":[10],"replaced":[11],"by":[12,99],"a":[13,21,33,88,100,113],"linguistically":[14],"valid":[15],"but":[16],"clinically":[17],"different":[18],"term,":[19],"pose":[20],"persistent":[22],"challenge":[23],"for":[24,50],"automated":[25],"error":[26,52],"detection":[27,117],"healthcare.":[29],"We":[30,109],"introduce":[31],"BLUEmed,":[32],"multi-agent":[34],"debate":[35,175],"framework":[36,181],"augmented":[37],"with":[38,47,125,186],"hybrid":[39],"Retrieval-Augmented":[40],"Generation":[41],"(RAG)":[42],"that":[43,104,137,170,179],"combines":[44],"evidence-grounded":[45],"reasoning":[46],"multi-perspective":[48],"verification":[49],"detection.":[53],"BLUEmed":[54,111,138],"decomposes":[55],"each":[56],"note":[58],"into":[59],"focused":[60],"sub-queries,":[61],"retrieves":[62],"source-partitioned":[63],"evidence":[64],"through":[65],"dense,":[66],"sparse,":[67],"and":[68,71,92,122,131,146,156,165,173,178,189],"online":[69],"retrieval,":[70],"assigns":[72],"two":[73,166],"domain":[74],"expert":[75],"agents":[76],"distinct":[77],"knowledge":[78],"bases":[79],"to":[80],"produce":[81],"independent":[82],"analyses;":[83],"when":[84],"the":[85,96,140,180],"experts":[86],"disagree,":[87],"structured":[89,174],"counter-argumentation":[90],"round":[91],"cross-source":[93],"adjudication":[94],"resolve":[95],"conflict,":[97],"followed":[98],"cascading":[101],"safety":[102],"layer":[103],"filters":[105],"common":[106],"false-positive":[107],"patterns.":[108],"evaluate":[110],"on":[112],"terminology":[115],"benchmark":[118],"under":[119,149],"both":[120,153],"zero-shot":[121],"few-shot":[123,150],"prompting":[124,167],"multiple":[126],"backbone":[127,163],"models":[128,164,185],"spanning":[129],"proprietary":[130],"open-source":[132],"families.":[133],"Experimental":[134],"results":[135],"show":[136],"achieves":[139],"best":[141],"accuracy":[142],"(69.13%),":[143],"ROC-AUC":[144],"(74.45%),":[145],"PR-AUC":[147],"(72.44%)":[148],"prompting,":[151],"outperforming":[152],"single-agent":[154],"RAG":[155],"debate-only":[157],"baselines.":[158],"Further":[159],"analyses":[160],"across":[161],"six":[162],"strategies":[168],"confirm":[169],"retrieval":[171],"augmentation":[172],"are":[176],"complementary,":[177],"benefits":[182],"most":[183],"from":[184],"sufficient":[187],"instruction-following":[188],"language":[191],"understanding.":[192]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-15T00:00:00"}