{"id":"https://openalex.org/W7166880652","doi":"https://doi.org/10.18653/v1/2026.findings-acl.693","title":"MedScore: Generalizable Factuality Evaluation of Open-ended Long-form Medical Answers by Domain-adapted Claim Decomposition and Verification","display_name":"MedScore: Generalizable Factuality Evaluation of Open-ended Long-form Medical Answers by Domain-adapted Claim Decomposition and Verification","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166880652","doi":"https://doi.org/10.18653/v1/2026.findings-acl.693"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.693","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.693","pdf_url":"https://aclanthology.org/2026.findings-acl.693.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.693.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139732187","display_name":"Heyuan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heyuan Huang","raw_affiliation_strings":["Center for Language and Speech Processing Johns Hopkins University Baltimore , MD 21218 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing Johns Hopkins University Baltimore , MD 21218 , USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139793777","display_name":"Alexandra DeLucia","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandra DeLucia","raw_affiliation_strings":["Center for Language and Speech Processing Johns Hopkins University Baltimore , MD 21218 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing Johns Hopkins University Baltimore , MD 21218 , USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119776225","display_name":"Vijay Murari Tiyyala","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Murari Tiyyala","raw_affiliation_strings":["Center for Language and Speech Processing Johns Hopkins University Baltimore , MD 21218 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing Johns Hopkins University Baltimore , MD 21218 , USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139716992","display_name":"Mark Dredze","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Dredze","raw_affiliation_strings":["Center for Language and Speech Processing Johns Hopkins University Baltimore , MD 21218 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing Johns Hopkins University Baltimore , MD 21218 , USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86897542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14149","last_page":"14180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5841000080108643,"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":0.5841000080108643,"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":0.13570000231266022,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.019099999219179153,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5072000026702881},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2401999980211258},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.22679999470710754},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.21220000088214874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6158999800682068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5435000061988831},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5072000026702881},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4034000039100647},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.24899999797344208},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2401999980211258},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2353000044822693},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.22679999470710754},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.21220000088214874},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.20309999585151672}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.693","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.693","pdf_url":"https://aclanthology.org/2026.findings-acl.693.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.693","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.693","pdf_url":"https://aclanthology.org/2026.findings-acl.693.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166880652.pdf","grobid_xml":"https://content.openalex.org/works/W7166880652.grobid-xml"},"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":[8,79,89,112,132,135,162,181],"convincing":[9],"responses,":[10],"they":[11,66],"are":[12,57,67],"not":[13],"necessarily":[14],"correct.This":[15],"is":[16,39,143],"especially":[17,40],"apparent":[18],"in":[19,138],"the":[20,52,62,167],"popular":[21],"decompose-then-verify":[22],"factuality":[23,55,153,175],"evaluation":[24,38,176],"pipeline,":[25],"where":[26],"LLMs":[27],"evaluate":[28],"generated":[29],"text":[30],"by":[31,157,177],"decomposing":[32],"it":[33],"into":[34,95,108],"individual,":[35],"valid":[36,96,110,125],"claims.Factuality":[37],"important":[41],"for":[42,61,173,184],"medical":[43,47,63,91,106],"answers,":[44,92],"since":[45],"incorrect":[46],"information":[48],"could":[49],"seriously":[50],"harm":[51],"patient.However,":[53],"existing":[54,128],"systems":[56],"a":[58,101],"poor":[59],"match":[60],"domain,":[64],"as":[65,77,123,127],"typically":[68],"only":[69],"evaluated":[70],"on":[71],"objective,":[72],"entity-centric,":[73],"formulaic":[74],"texts":[75],"such":[76],"biographies":[78],"historical":[80],"topics.This":[81],"differs":[82],"from":[83],"condition-dependent,":[84],"conversational,":[85],"hypothetical,":[86],"sentence-structure":[87],"diverse,":[88],"subjective":[90],"making":[93],"decomposition":[94,158],"facts":[97,111,126],"challenging.We":[98],"propose":[99],"MedScore,":[100],"new":[102],"pipeline":[103,183],"to":[104,120,145],"decompose":[105],"answers":[107],"condition-aware":[109],"verify":[113],"against":[114],"in-domain":[115],"corpora.Our":[116],"method":[117],"extracts":[118],"up":[119],"three":[121],"times":[122],"many":[124],"methods,":[129],"reducing":[130],"hallucination":[131],"vague":[133],"references,":[134],"retaining":[136],"condition-dependency":[137],"facts.We":[139],"also":[140],"find":[141],"MedScore":[142],"generalizable":[144,180],"non-medical":[146],"domains":[147],"without":[148],"any":[149],"specific":[150],"tuning.The":[151],"resulting":[152],"score":[154],"substantially":[155],"varies":[156],"method,":[159],"verification":[160],"corpus,":[161],"used":[163],"backbone":[164],"LLM,":[165],"highlighting":[166],"importance":[168],"of":[169],"customizing":[170],"each":[171],"step":[172],"reliable":[174],"using":[178],"our":[179],"modularized":[182],"domain":[185],"adaptation.":[186],"1":[187]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}