{"id":"https://openalex.org/W7160445418","doi":"https://doi.org/10.48550/arxiv.2605.03476","title":"CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification","display_name":"CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification","publication_year":2026,"publication_date":"2026-05-05","ids":{"openalex":"https://openalex.org/W7160445418","doi":"https://doi.org/10.48550/arxiv.2605.03476"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.03476","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03476","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.03476","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135437543","display_name":"Severin Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Severin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103382615","display_name":"Xiao Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135472938","display_name":"Xiaopeng He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Xiaopeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135534170","display_name":"Guangsu Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Guangsu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135512001","display_name":"Dongsuk Oh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oh, Dongsuk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.8291000127792358,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.8291000127792358,"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/T10028","display_name":"Topic Modeling","score":0.09000000357627869,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.013199999928474426,"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/pipeline","display_name":"Pipeline (software)","score":0.5328999757766724},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5031999945640564},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.4999000132083893},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4936000108718872},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4683000147342682},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4018999934196472},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.3472999930381775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6980000138282776},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5328999757766724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5245000123977661},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5016999840736389},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4936000108718872},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45719999074935913},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3596999943256378},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.03476","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03476","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.03476","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03476","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Discharge":[0],"summaries":[1],"require":[2],"extracting":[3],"critical":[4],"information":[5],"from":[6,74,93,115],"lengthy":[7],"electronic":[8],"health":[9],"records":[10],"(EHRs),":[11],"a":[12,53,70,79,110,153],"process":[13],"that":[14,37,170],"is":[15],"labor-intensive":[16],"when":[17],"performed":[18],"manually.":[19],"Large":[20],"language":[21],"models":[22],"(LLMs)":[23],"can":[24],"improve":[25],"generation":[26],"efficiency;":[27],"however,":[28],"they":[29],"are":[30],"prone":[31],"to":[32,44,96],"producing":[33,185],"faithfulness":[34,63],"hallucinations,":[35],"statements":[36],"contradict":[38],"source":[39],"records,":[40],"posing":[41],"direct":[42,97],"risks":[43],"patient":[45],"safety.":[46],"To":[47],"address":[48],"this,":[49],"we":[50],"present":[51],"CuraView,":[52],"multi-agent":[54],"framework":[55],"for":[56,124,189],"sentence-level":[57,84],"detection":[58,129],"and":[59,77,87,102,145,161,164,193],"evidence-grounded":[60],"explanation":[61],"of":[62,112,134,148,180],"hallucinations":[64],"in":[65],"discharge":[66],"summaries.":[67],"CuraView":[68,108],"constructs":[69],"GraphRAG-based":[71],"knowledge":[72],"graph":[73,172],"patient-level":[75],"EHRs":[76],"implements":[78],"closed-loop":[80],"generation-detection":[81],"pipeline":[82],"with":[83,119],"evidence":[85,91,104],"retrieval":[86,173],"classification":[88],"spanning":[89],"four":[90],"grades":[92],"strong":[94],"support":[95],"contradiction":[98],"(E1-E4),":[99],"yielding":[100],"structured":[101],"interpretable":[103],"chains.":[105],"We":[106],"evaluate":[107],"on":[109,136,150],"subset":[111],"250":[113],"patients":[114,121],"the":[116,137,158,177],"Discharge-Me":[117],"benchmark,":[118],"50":[120],"held":[122],"out":[123],"testing.":[125],"Our":[126],"fine-tuned":[127],"Qwen3-14B":[128],"model":[130,160,191],"achieves":[131],"an":[132,146],"F1":[133,147],"0.831":[135],"safety-critical":[138],"E4":[139],"metric":[140],"(90.9%":[141],"recall,":[142],"76.5%":[143],"precision)":[144],"0.823":[149],"E3+E4,":[151],"representing":[152],"50.0%":[154],"relative":[155],"improvement":[156],"over":[157],"base":[159],"outperforming":[162],"RAGTruth-style":[163],"QAGS-style":[165],"baselines.":[166],"These":[167],"results":[168],"demonstrate":[169],"evidence-chain-based":[171],"verification":[174],"substantially":[175],"improves":[176],"factual":[178],"reliability":[179],"clinical":[181],"documentation,":[182],"while":[183],"simultaneously":[184],"reusable":[186],"annotated":[187],"datasets":[188],"downstream":[190],"training":[192],"distillation.":[194]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-07T00:00:00"}