{"id":"https://openalex.org/W7140073993","doi":"https://doi.org/10.18653/v1/2026.eacl-long.111","title":"Reasoning or Knowledge: Stratified Evaluation of Biomedical LLMs","display_name":"Reasoning or Knowledge: Stratified Evaluation of Biomedical LLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140073993","doi":"https://doi.org/10.18653/v1/2026.eacl-long.111"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.111","doi":"https://doi.org/10.18653/v1/2026.eacl-long.111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.111","pdf_url":"https://aclanthology.org/2026.eacl-long.111.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.eacl-long.111.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026274141","display_name":"Rahul Thapa","orcid":"https://orcid.org/0000-0002-1137-955X","observed_orcids":["https://orcid.org/0000-0002-1137-955X"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Thapa","raw_affiliation_strings":["Stanford University","Together AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Together AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130352193","display_name":"Qingyang Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingyang Wu","raw_affiliation_strings":["Together AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Together AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002340225","display_name":"Kevin Wu","orcid":"https://orcid.org/0000-0002-4786-9796","observed_orcids":["https://orcid.org/0000-0002-4786-9796","https://orcid.org/0000-0001-7112-1190"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Wu","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014149768","display_name":"Harrison G. Zhang","orcid":"https://orcid.org/0000-0001-6679-1464","observed_orcids":["https://orcid.org/0000-0001-6679-1464"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harrison G Zhang","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076640237","display_name":"Angela Zhang","orcid":"https://orcid.org/0000-0003-0906-6770","observed_orcids":["https://orcid.org/0000-0003-0906-6770"]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Angela Zhang","raw_affiliation_strings":["University of California , San Francisco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , San Francisco","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095767086","display_name":"Eric Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Wu","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077279992","display_name":"Haotian Ye","orcid":"https://orcid.org/0009-0005-8486-0626","observed_orcids":["https://orcid.org/0009-0005-8486-0626"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haotian Ye","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005779176","display_name":"James Zou","orcid":"https://orcid.org/0000-0001-8880-4764","observed_orcids":["https://orcid.org/0000-0001-8880-4764"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Zou","raw_affiliation_strings":["Stanford University","Together AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Together AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.2423,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94754411,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2450","last_page":"2483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.302700012922287,"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"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.302700012922287,"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/T10028","display_name":"Topic Modeling","score":0.28519999980926514,"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":0.16609999537467957,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.671999990940094},{"id":"https://openalex.org/keywords/biomedical-question-answering","display_name":"biomedical question answering","score":0.5830000042915344}],"concepts":[{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.33309999108314514},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.31049999594688416},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3012999892234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.29190000891685486},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2689000070095062},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2671999931335449},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C91375879","wikidata":"https://www.wikidata.org/wiki/Q15473274","display_name":"Environmental planning","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.25609999895095825},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.111","doi":"https://doi.org/10.18653/v1/2026.eacl-long.111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.111","pdf_url":"https://aclanthology.org/2026.eacl-long.111.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.111","doi":"https://doi.org/10.18653/v1/2026.eacl-long.111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.111","pdf_url":"https://aclanthology.org/2026.eacl-long.111.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140073993.pdf","grobid_xml":"https://content.openalex.org/works/W7140073993.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4412889963","https://openalex.org/W4411119158","https://openalex.org/W4416167878","https://openalex.org/W4416035050","https://openalex.org/W7140039778","https://openalex.org/W4415795765","https://openalex.org/W7140106595","https://openalex.org/W4407757306","https://openalex.org/W7160122692","https://openalex.org/W7140087520"],"abstract_inverted_index":{"Rahul":[0],"Thapa,":[1],"Qingyang":[2],"Wu,":[3,5,12],"Kevin":[4],"Harrison":[6],"G":[7],"Zhang,":[8,10],"Angela":[9],"Eric":[11],"Haotian":[13],"Ye,":[14],"James":[15],"Zou.":[16],"Proceedings":[17],"of":[18,22,26],"the":[19,23,27],"19th":[20],"Conference":[21],"European":[24],"Chapter":[25],"Association":[28],"for":[29],"Computational":[30],"Linguistics":[31],"(Volume":[32],"1:":[33],"Long":[34],"Papers).":[35],"2026.":[36]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-03-24T00:00:00"}
