{"id":"https://openalex.org/W4415946405","doi":"https://doi.org/10.48550/arxiv.2505.18452","title":"MedScore: Generalizable Factuality Evaluation of Free-Form Medical Answers by Domain-adapted Claim Decomposition and Verification","display_name":"MedScore: Generalizable Factuality Evaluation of Free-Form Medical Answers by Domain-adapted Claim Decomposition and Verification","publication_year":2025,"publication_date":"2025-05-24","ids":{"openalex":"https://openalex.org/W4415946405","doi":"https://doi.org/10.48550/arxiv.2505.18452"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.18452","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.18452","pdf_url":"https://arxiv.org/pdf/2505.18452","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.18452","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109875808","display_name":"Heyuan Huang","orcid":"https://orcid.org/0009-0000-0320-3629"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Huang, Heyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045330788","display_name":"Alexandra DeLucia","orcid":"https://orcid.org/0000-0003-4325-9170"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"DeLucia, Alexandra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119776225","display_name":"Vijay Murari Tiyyala","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiyyala, Vijay Murari","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024437840","display_name":"Mark Dredze","orcid":"https://orcid.org/0000-0002-0422-2474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dredze, Mark","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109875808"],"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":0.552299976348877,"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":0.552299976348877,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.13920000195503235,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.031199999153614044,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.8349000215530396},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.6809999942779541},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5511000156402588},{"id":"https://openalex.org/keywords/harm","display_name":"Harm","score":0.4830000102519989},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.2806999981403351}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8349000215530396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6823999881744385},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.6809999942779541},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5511000156402588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.512499988079071},{"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/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35350000858306885},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.2806999981403351},{"id":"https://openalex.org/C2778258933","wikidata":"https://www.wikidata.org/wiki/Q16918986","display_name":"Decomposition method (queueing theory)","level":2,"score":0.2687000036239624}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.18452","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.18452","pdf_url":"https://arxiv.org/pdf/2505.18452","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"doi:10.48550/arxiv.2505.18452","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.18452","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":"pmh:oai:arXiv.org:2505.18452","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.18452","pdf_url":"https://arxiv.org/pdf/2505.18452","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"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":{"While":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"can":[5],"generate":[6],"fluent":[7],"and":[8,82,93,118,138,141,157,176],"convincing":[9],"responses,":[10],"they":[11,69],"are":[12,60,70],"not":[13],"necessarily":[14],"correct.":[15],"This":[16,85],"is":[17,41],"especially":[18,42],"apparent":[19],"in":[20,144],"the":[21,33,54,65,162],"popular":[22],"decompose-then-verify":[23],"factuality":[24,58,148,170],"evaluation":[25,40,171],"pipeline,":[26],"where":[27],"LLMs":[28],"evaluate":[29],"generations":[30,34],"by":[31,152,172],"decomposing":[32],"into":[35,100,114],"individual,":[36],"valid":[37,101,116,131],"claims.":[38],"Factuality":[39],"important":[43],"for":[44,64,168,179],"medical":[45,49,66,95,112],"answers,":[46,96],"since":[47],"incorrect":[48],"information":[50],"could":[51],"seriously":[52],"harm":[53],"patient.":[55],"However,":[56],"existing":[57,134],"systems":[59],"a":[61,107],"poor":[62],"match":[63],"domain,":[67],"as":[68,80],"typically":[71],"only":[72],"evaluated":[73],"on":[74],"objective,":[75],"entity-centric,":[76],"formulaic":[77],"texts":[78],"such":[79],"biographies":[81],"historical":[83],"topics.":[84],"differs":[86],"from":[87],"condition-dependent,":[88],"conversational,":[89],"hypothetical,":[90],"sentence-structure":[91],"diverse,":[92],"subjective":[94],"which":[97],"makes":[98],"decomposition":[99,153],"facts":[102,117,132],"challenging.":[103],"We":[104],"propose":[105],"MedScore,":[106],"new":[108],"pipeline":[109,178],"to":[110,127],"decompose":[111],"answers":[113],"condition-aware":[115],"verify":[119],"against":[120],"in-domain":[121],"corpora.":[122],"Our":[123],"method":[124],"extracts":[125],"up":[126],"three":[128],"times":[129],"more":[130],"than":[133],"methods,":[135],"reducing":[136],"hallucination":[137],"vague":[139],"references,":[140],"retaining":[142],"condition-dependency":[143],"facts.":[145],"The":[146],"resulting":[147],"score":[149],"substantially":[150],"varies":[151],"method,":[154],"verification":[155],"corpus,":[156],"used":[158],"backbone":[159],"LLM,":[160],"highlighting":[161],"importance":[163],"of":[164],"customizing":[165],"each":[166],"step":[167],"reliable":[169],"using":[173],"our":[174],"generalizable":[175],"modularized":[177],"domain":[180],"adaptation.":[181]},"counts_by_year":[],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-10T00:00:00"}