{"id":"https://openalex.org/W4416036367","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.598","title":"ReEvalMed: Rethinking Medical Report Evaluation by Aligning Metrics with Real-World Clinical Judgment","display_name":"ReEvalMed: Rethinking Medical Report Evaluation by Aligning Metrics with Real-World Clinical Judgment","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036367","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.598"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.598","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.598","pdf_url":"https://aclanthology.org/2025.emnlp-main.598.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.598.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101653828","display_name":"Ruochen Li","orcid":"https://orcid.org/0000-0002-4341-6474"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ruochen Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362088","display_name":"Jun Li","orcid":"https://orcid.org/0000-0003-3387-695X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037729712","display_name":"Bailiang Jian","orcid":"https://orcid.org/0009-0009-2419-0420"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bailiang Jian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049520209","display_name":"Kun Yuan","orcid":"https://orcid.org/0009-0003-9425-7842"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Yuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010382904","display_name":"Youxiang Zhu","orcid":"https://orcid.org/0009-0000-7294-1596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Youxiang Zhu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101653828"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1843191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11823","last_page":"11837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5001999735832214,"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":0.5001999735832214,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.09780000150203705,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.06679999828338623,"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/clinical-judgment","display_name":"Clinical judgment","score":0.689300000667572},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.31310001015663147},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2766000032424927},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.2705000042915344},{"id":"https://openalex.org/keywords/self-report-study","display_name":"Self-report study","score":0.2578999996185303}],"concepts":[{"id":"https://openalex.org/C3020452639","wikidata":"https://www.wikidata.org/wiki/Q454812","display_name":"Clinical judgment","level":2,"score":0.689300000667572},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4244999885559082},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.36800000071525574},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.36419999599456787},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2809999883174896},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C54998920","wikidata":"https://www.wikidata.org/wiki/Q16255102","display_name":"Self-report study","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.598","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.598","pdf_url":"https://aclanthology.org/2025.emnlp-main.598.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.598","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.598","pdf_url":"https://aclanthology.org/2025.emnlp-main.598.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036367.pdf","grobid_xml":"https://content.openalex.org/works/W4416036367.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automatically":[0],"generated":[1,30],"radiology":[2],"reports":[3],"often":[4],"receive":[5],"high":[6],"scores":[7],"from":[8],"existing":[9,85],"evaluation":[10,36,121],"metrics":[11,25,39,86],"but":[12],"fail":[13],"to":[14,98],"earn":[15],"clinicians'":[16],"trust.This":[17],"gap":[18],"reveals":[19],"fundamental":[20],"flaws":[21],"in":[22,91],"how":[23],"current":[24],"assess":[26],"the":[27,33],"quality":[28],"of":[29,37,66],"reports.We":[31],"rethink":[32],"design":[34],"and":[35,40,54,61,69,80,87,106],"these":[38],"propose":[41],"a":[42,63],"clinically":[43,48,100,119],"grounded":[44,49],"Meta-Evaluation":[45],"framework.We":[46],"define":[47],"criteria":[50],"spanning":[51],"clinical":[52,77,93],"alignment":[53],"key":[55],"metric":[56],"capabilities,":[57],"including":[58],"discrimination,":[59],"robustness,":[60],"monotonicity.Using":[62],"fine-grained":[64],"dataset":[65],"ground":[67],"truth":[68],"rewritten":[70],"report":[71],"pairs":[72],"annotated":[73],"with":[74],"error":[75,110],"types,":[76],"significance":[78],"labels,":[79],"explanations,":[81],"we":[82],"systematically":[83],"evaluate":[84],"reveal":[88],"their":[89],"limitations":[90],"interpreting":[92],"semantics,":[94],"such":[95],"as":[96],"failing":[97],"distinguish":[99],"significant":[101],"errors,":[102],"over-penalizing":[103],"harmless":[104],"variations,":[105],"lacking":[107],"consistency":[108],"across":[109],"severity":[111],"levels.Our":[112],"framework":[113],"offers":[114],"guidance":[115],"for":[116],"building":[117],"more":[118],"reliable":[120],"methods.Project":[122],"link":[123],"is":[124],"https:":[125],"//ruochenli99.github.io/ReEvalMed/":[126]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-11-08T00:00:00"}