{"id":"https://openalex.org/W4416557050","doi":"https://doi.org/10.18653/v1/2026.findings-acl.151","title":"DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models","display_name":"DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416557050","doi":"https://doi.org/10.18653/v1/2026.findings-acl.151"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.151","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.151","pdf_url":"https://aclanthology.org/2026.findings-acl.151.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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.151.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003906648","display_name":"Yu Zhu","orcid":"https://orcid.org/0009-0000-3340-1060"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yakun Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017431694","display_name":"Zhongzhen Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongzhen Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033854414","display_name":"Linjie Mu","orcid":"https://orcid.org/0000-0003-2883-4173"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linjie Mu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114094222","display_name":"Yutong Huang","orcid":"https://orcid.org/0009-0006-2380-9795"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yutong Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101563764","display_name":"Wei Nie","orcid":"https://orcid.org/0000-0001-6878-7936"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Nie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726050","display_name":"Jiaji Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaji Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066553616","display_name":"Shaoting Zhang","orcid":"https://orcid.org/0000-0002-8719-448X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaoting Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354997","display_name":"Pengfei Liu","orcid":"https://orcid.org/0000-0001-9030-1875"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330746","display_name":"Xiaofan Zhang","orcid":"https://orcid.org/0009-0005-2962-3644"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.01076716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3074","last_page":"3098"},"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":0.4634999930858612,"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":0.4634999930858612,"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":0.14880000054836273,"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/T12574","display_name":"Clinical Reasoning and Diagnostic Skills","score":0.13379999995231628,"subfield":{"id":"https://openalex.org/subfields/2714","display_name":"Family Practice"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.7620000243186951},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7387999892234802},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6898999810218811},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5300999879837036},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.33970001339912415},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.3122999966144562}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7620000243186951},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7387999892234802},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6898999810218811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6887000203132629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.534500002861023},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5300999879837036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4691999852657318},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3695000112056732},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.3122999966144562},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C82157600","wikidata":"https://www.wikidata.org/wiki/Q2671652","display_name":"Diagnostic test","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.151","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.151","pdf_url":"https://aclanthology.org/2026.findings-acl.151.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"},{"id":"pmh:oai:arXiv.org:2505.14107","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.14107","pdf_url":"https://arxiv.org/pdf/2505.14107","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.14107","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.14107","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.findings-acl.151","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.151","pdf_url":"https://aclanthology.org/2026.findings-acl.151.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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416557050.pdf","grobid_xml":"https://content.openalex.org/works/W4416557050.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"emergence":[1],"of":[2,8,47,53,78,81,114],"groundbreaking":[3],"large":[4,162],"language":[5,163],"models":[6,49,164],"capable":[7],"performing":[9],"complex":[10,25],"reasoning":[11,140,170,182],"tasks":[12],"holds":[13],"significant":[14,157],"promise":[15],"for":[16,188,200],"addressing":[17],"various":[18],"scientific":[19],"challenges,":[20],"including":[21],"those":[22],"arising":[23],"in":[24,34,57,98,160,179],"clinical":[26,94,168,190],"scenarios.To":[27],"enable":[28],"their":[29],"safe":[30],"and":[31,67,85,116,122,144,150,197,203],"effective":[32,186],"deployment":[33],"real-world":[35,189],"healthcare":[36],"settings,":[37],"it":[38],"is":[39,104],"urgently":[40],"necessary":[41],"to":[42,71,129,175],"benchmark":[43,69,103,196],"the":[44,51,137,195],"diagnostic":[45,60,75,169,181,191],"capabilities":[46],"current":[48,161],"systematically.Given":[50],"limitations":[52],"existing":[54],"medical":[55,90,101],"benchmarks":[56],"evaluating":[58],"advanced":[59,139],"reasoning,":[61],"we":[62,173],"present":[63],"DiagnosisArena,":[64],"a":[65,107,156],"comprehensive":[66],"challenging":[68],"designed":[70],"rigorously":[72],"assess":[73],"professional-level":[74],"competence.DiagnosisArena":[76],"consists":[77],"1,113":[79],"pairs":[80],"segmented":[82],"patient":[83],"cases":[84],"corresponding":[86],"diagnoses,":[87],"spanning":[88],"28":[89],"specialties,":[91],"deriving":[92],"from":[93],"case":[95],"reports":[96],"published":[97],"10":[99],"top-tier":[100],"journals.The":[102],"developed":[105],"through":[106],"meticulous":[108],"construction":[109],"pipeline,":[110],"involving":[111],"multiple":[112],"rounds":[113],"screening":[115],"review":[117],"by":[118],"both":[119],"AI":[120],"systems":[121],"human":[123],"experts,":[124],"with":[125,167],"thorough":[126],"checks":[127],"conducted":[128],"prevent":[130],"data":[131],"leakage.Our":[132],"study":[133],"reveals":[134],"that":[135],"even":[136],"most":[138],"models,":[141],"o3-mini,":[142],"o1,":[143],"DeepSeek-R1,":[145],"achieve":[146],"only":[147],"45.82%,":[148],"31.09%,":[149],"17.79%":[151],"accuracy,":[152],"respectively.This":[153],"finding":[154],"highlights":[155],"generalization":[158],"bottleneck":[159],"when":[165],"faced":[166],"challenges.Through":[171],"Di-agnosisArena,":[172],"aim":[174],"drive":[176],"further":[177,201],"advancements":[178],"AI's":[180],"capabilities,":[183],"enabling":[184],"more":[185],"solutions":[187],"challenges.We":[192],"openly":[193],"share":[194],"evaluation":[198],"tools":[199],"research":[202],"development":[204],"1":[205],".":[206]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}