{"id":"https://openalex.org/W4417127572","doi":"https://doi.org/10.18653/v1/2026.acl-long.1218","title":"Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation","display_name":"Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417127572","doi":"https://doi.org/10.18653/v1/2026.acl-long.1218"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1218","pdf_url":"https://aclanthology.org/2026.acl-long.1218.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1218.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090809240","display_name":"Xiangxu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxu Zhang","raw_affiliation_strings":["GSAI , Renmin University of China ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GSAI , Renmin University of China ,","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101376426","display_name":"Lei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":["GSAI , Renmin University of China ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GSAI , Renmin University of China ,","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082037867","display_name":"Yanyun Zhou","orcid":"https://orcid.org/0000-0001-6468-1309"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyun Zhou","raw_affiliation_strings":["GSAI , Renmin University of China ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GSAI , Renmin University of China ,","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111622886","display_name":"Xiao Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422741","display_name":"Yingying Zhang","orcid":"https://orcid.org/0000-0001-5741-1239"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Zhang","raw_affiliation_strings":["Tencent Jarvis Lab ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Jarvis Lab ,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020337169","display_name":"Wu Xian","orcid":"https://orcid.org/0000-0002-5315-5634"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Wu","raw_affiliation_strings":["Tencent Jarvis Lab ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Jarvis Lab ,","institution_ids":["https://openalex.org/I2250653659"]}]}],"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":0.01503268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26454","last_page":"26493"},"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":0.4189000129699707,"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":0.4189000129699707,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.334199994802475,"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":0.065700002014637,"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/medical-diagnosis","display_name":"Medical diagnosis","score":0.7031000256538391},{"id":"https://openalex.org/keywords/excellence","display_name":"Excellence","score":0.6927000284194946},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5583999752998352},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.5202999711036682},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.477400004863739},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.384799987077713}],"concepts":[{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.7031000256538391},{"id":"https://openalex.org/C2777352838","wikidata":"https://www.wikidata.org/wiki/Q5419420","display_name":"Excellence","level":2,"score":0.6927000284194946},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5583999752998352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5468999743461609},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.477400004863739},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.40700000524520874},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3614000082015991},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26420000195503235},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1218","pdf_url":"https://aclanthology.org/2026.acl-long.1218.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.09275","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.09275","pdf_url":"https://arxiv.org/pdf/2510.09275","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.09275","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.09275","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:10.18653/v1/2026.acl-long.1218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1218","pdf_url":"https://aclanthology.org/2026.acl-long.1218.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417127572.pdf","grobid_xml":"https://content.openalex.org/works/W4417127572.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Medical":[0],"diagnostics":[1,92,183],"is":[2,9],"a":[3,60,87,95],"high-stakes":[4],"and":[5,45,77,97,121,146,158],"complex":[6],"domain":[7],"that":[8,41,93,112,150,178],"critical":[10],"to":[11,129],"patient":[12],"care.However,":[13],"current":[14],"evaluations":[15,58],"of":[16,27,51,73,101,162],"large":[17],"language":[18],"models":[19],"(LLMs)":[20],"remain":[21,65],"limited":[22,71],"in":[23],"capturing":[24],"key":[25],"challenges":[26],"clinical":[28],"diagnostic":[29,102,168],"scenarios.Most":[30],"rely":[31],"on":[32,138],"benchmarks":[33],"derived":[34],"from":[35],"public":[36],"exams,":[37],"raising":[38],"contamination":[39],"bias":[40],"can":[42],"inflate":[43],"performance,":[44],"they":[46],"overlook":[47],"the":[48,172,197],"confounded":[49,167],"nature":[50],"real":[52],"consultations":[53],"beyond":[54,79],"textbook":[55],"cases.Recent":[56],"dynamic":[57,88,152],"offer":[59],"promising":[61],"alternative,":[62],"but":[63],"often":[64],"insufficient":[66],"for":[67,90,175],"diagnosis-oriented":[68],"benchmarking,":[69],"with":[70],"coverage":[72],"clinically":[74,114,141,166,185],"grounded":[75,115,186],"confounders":[76],"trustworthiness":[78],"accuracy.To":[80],"address":[81],"these":[82],"gaps,":[83],"we":[84],"propose":[85],"DyReMe,":[86],"benchmark":[89],"medical":[91,182],"provides":[94],"controlled":[96],"scalable":[98],"stress":[99],"test":[100],"robustness.Unlike":[103],"static":[104],"exam-style":[105],"questions,":[106],"DyReMe":[107,135],"generates":[108],"fresh,":[109],"consultation-style":[110],"cases":[111],"incorporate":[113],"confounders,":[116],"such":[117],"as":[118],"differential":[119],"diagnoses":[120],"common":[122],"misdiagnosis":[123],"factors.It":[124],"also":[125],"varies":[126],"expression":[127],"styles":[128],"capture":[130],"heterogeneous":[131],"patient-style":[132],"descriptions.Beyond":[133],"accuracy,":[134],"evaluates":[136],"LLMs":[137,164],"three":[139],"additional":[140],"relevant":[142],"dimensions:":[143],"veracity,":[144],"helpfulness,":[145],"consistency.Our":[147],"experiments":[148],"show":[149],"this":[151],"approach":[153],"yields":[154],"more":[155],"challenging":[156],"assessments":[157],"exposes":[159],"substantial":[160],"weaknesses":[161],"stateof-the-art":[163],"under":[165,184],"settings.These":[169],"findings":[170],"highlight":[171],"urgent":[173],"need":[174],"evaluation":[176],"frameworks":[177],"better":[179],"assess":[180],"trustworthy":[181],"confounders.":[187],"1":[188,192],"*":[189],"Corresponding":[190],"Author":[191],"We":[193],"have":[194],"officially":[195],"released":[196],"code":[198],"here.To":[199],"support":[200],"continual":[201],"evaluation,":[202]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-14T00:00:00"}