{"id":"https://openalex.org/W7204452336","doi":"https://doi.org/10.18653/v1/2026.sigdial-1.58","title":"MTDiag: A Multi-Turn Diagnostic Dataset Towards Clinically Meaningful LLM Evaluation","display_name":"MTDiag: A Multi-Turn Diagnostic Dataset Towards Clinically Meaningful LLM Evaluation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204452336","doi":"https://doi.org/10.18653/v1/2026.sigdial-1.58"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.sigdial-1.58","doi":"https://doi.org/10.18653/v1/2026.sigdial-1.58","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.sigdial-1.58","pdf_url":"https://aclanthology.org/2026.sigdial-1.58.pdf","source":{"id":"https://openalex.org/S4306417680","display_name":"Annual Meeting of the Special Interest Group on Discourse and Dialogue","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.sigdial-1.58.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119181741","display_name":"Pia Chouayfati","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pia Chouayfati","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093567838","display_name":"Alexander M. Fichtl","orcid":"https://orcid.org/0009-0001-9875-0197","observed_orcids":["https://orcid.org/0009-0001-9875-0197"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander M. Fichtl","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041007080","display_name":"Miriam Ansch\u00fctz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Miriam Ansch\u00fctz","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084100471","display_name":"George Doumat","orcid":"https://orcid.org/0000-0003-3931-2709","observed_orcids":["https://orcid.org/0000-0003-3931-2709"]},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Doumat","raw_affiliation_strings":["Department of Internal Medicine , UT Southwestern"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine , UT Southwestern","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139809972","display_name":"Georg Groh","orcid":"https://orcid.org/0000-0002-5942-2297","observed_orcids":["https://orcid.org/0000-0002-5942-2297"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georg Groh","raw_affiliation_strings":["Technical University of Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.70548278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"821","last_page":"840"},"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":0.9477999806404114,"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":0.9477999806404114,"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":0.03550000116229057,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.00419999985024333,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6520000100135803},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.6970000267028809},{"id":"https://openalex.org/keywords/multi-turn-dialogue","display_name":"multi-turn dialogue","score":0.7850000262260437},{"id":"https://openalex.org/keywords/diagnosis","display_name":"diagnosis","score":0.8169999718666077},{"id":"https://openalex.org/keywords/diagnostic-agents","display_name":"diagnostic agents","score":0.6990000009536743},{"id":"https://openalex.org/keywords/differential-diagnosis","display_name":"differential diagnosis","score":0.9350000023841858},{"id":"https://openalex.org/keywords/clinical-knowledge-base","display_name":"clinical knowledge base","score":0.49300000071525574},{"id":"https://openalex.org/keywords/umls","display_name":"UMLS","score":0.7559999823570251},{"id":"https://openalex.org/keywords/icd-10","display_name":"ICD-10","score":0.8840000033378601},{"id":"https://openalex.org/keywords/emergency-department-presentation","display_name":"emergency department presentation","score":0.8489999771118164},{"id":"https://openalex.org/keywords/utterance-generation","display_name":"utterance production","score":0.722000002861023}],"concepts":[{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6244000196456909},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48579999804496765},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.4397999942302704},{"id":"https://openalex.org/C3020132585","wikidata":"https://www.wikidata.org/wiki/Q2671652","display_name":"Diagnostic accuracy","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4066999852657318},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3458999991416931},{"id":"https://openalex.org/C82157600","wikidata":"https://www.wikidata.org/wiki/Q2671652","display_name":"Diagnostic test","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32919999957084656},{"id":"https://openalex.org/C2983449737","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Clinical diagnosis","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C163763905","wikidata":"https://www.wikidata.org/wiki/Q17075943","display_name":"Precision medicine","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C206179267","wikidata":"https://www.wikidata.org/wiki/Q188952","display_name":"Medical history","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29019999504089355},{"id":"https://openalex.org/C19648533","wikidata":"https://www.wikidata.org/wiki/Q691640","display_name":"Evidence-based medicine","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C177713679","wikidata":"https://www.wikidata.org/wiki/Q679690","display_name":"Intensive care medicine","level":1,"score":0.2606000006198883},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25949999690055847},{"id":"https://openalex.org/C535046627","wikidata":"https://www.wikidata.org/wiki/Q30612","display_name":"Clinical trial","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C3018949938","wikidata":"https://www.wikidata.org/wiki/Q17166101","display_name":"Text messaging","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2535000145435333},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.250900000333786}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.sigdial-1.58","doi":"https://doi.org/10.18653/v1/2026.sigdial-1.58","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.sigdial-1.58","pdf_url":"https://aclanthology.org/2026.sigdial-1.58.pdf","source":{"id":"https://openalex.org/S4306417680","display_name":"Annual Meeting of the Special Interest Group on Discourse and Dialogue","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.25085","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25085","pdf_url":"https://arxiv.org/pdf/2608.25085","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,"listed_in":[],"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.25085","doi":"https://doi.org/10.48550/arxiv.2608.25085","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.25085","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.sigdial-1.58","doi":"https://doi.org/10.18653/v1/2026.sigdial-1.58","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.sigdial-1.58","pdf_url":"https://aclanthology.org/2026.sigdial-1.58.pdf","source":{"id":"https://openalex.org/S4306417680","display_name":"Annual Meeting of the Special Interest Group on Discourse and Dialogue","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2555749475","display_name":null,"funder_award_id":"01IS22093A","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G3589708518","display_name":null,"funder_award_id":"01IS22093A-E","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204452336.pdf","grobid_xml":"https://content.openalex.org/works/W7204452336.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7160831892","https://openalex.org/W7118689623","https://openalex.org/W7167622529","https://openalex.org/W7213017671","https://openalex.org/W4413481664","https://openalex.org/W7151226796","https://openalex.org/W7117755256","https://openalex.org/W7163395773","https://openalex.org/W7117958962","https://openalex.org/W4415269770"],"abstract_inverted_index":{"Clinical":[0],"diagnosis":[1,114],"is":[2],"fundamentally":[3],"interactive":[4],"and":[5,49,74,88,104,124,138],"incremental,":[6],"yet":[7],"the":[8,101,117,125,153,162,168],"dominant":[9],"paradigm":[10],"for":[11,143,152],"evaluating":[12,144],"Large":[13],"Language":[14],"Models":[15],"(LLMs)":[16],"in":[17,39,52,100,171],"medicine":[18],"remains":[19],"static":[20],"QA":[21],"benchmarks":[22,26],"or":[23],"template-based":[24],"dialogues.These":[25],"say":[27],"little":[28],"about":[29],"whether":[30],"a":[31,36,40,61,95,120],"model":[32],"can":[33],"serve":[34],"as":[35,83,85,146],"diagnostic":[37,64,147,150],"agent":[38],"dynamic":[41],"clinical":[42,131,140],"encounter,":[43],"with":[44,112],"LLMs":[45,145],"showing":[46],"significant":[47],"accuracy":[48],"reliability":[50],"degradation":[51],"multi-turn":[53,156],"settings.To":[54],"address":[55],"this":[56],"issue,":[57],"we":[58,136],"present":[59],"MTDiag,":[60],"large":[62],"multiturn":[63],"dialogue":[65],"dataset":[66,127],"constructed":[67],"from":[68],"three":[69],"heterogeneous":[70],"sources:":[71],"DDX-Plus,":[72],"MIMIC-IV,":[73],"published":[75],"case":[76],"reports":[77],"(AJCR),":[78],"covering":[79],"common":[80],"ED":[81],"presentations":[82],"well":[84],"long-tail":[86],"rare":[87],"atypical":[89],"conditions.All":[90],"cases":[91],"are":[92],"normalized":[93],"into":[94,133],"canonical":[96],"PatientVector":[97,118],"schema":[98],"anchored":[99],"most":[102],"comprehensive":[103],"widely-adopted":[105],"medical":[106],"knowledge":[107],"bases":[108],"(UMLS":[109],"concept":[110,170],"identifiers,":[111],"ICD-10":[113],"codes).We":[115],"release":[116],"schema,":[119],"UserLM-8Bbased":[121],"utterance-generation":[122],"pipeline,":[123],"physician-validated":[126],"that":[128],"converts":[129],"structured":[130],"evidence":[132],"natural-language":[134],"utterances.Importantly,":[135],"introduce":[137],"motivate":[139],"knowledge-grounded":[141],"metrics":[142],"agents,":[148],"beyond":[149],"accuracy,":[151],"task":[154],"of":[155,161],"differential":[157],"diagnosis.cross-walk":[158],"between":[159],"any":[160],"vocabularies":[163],"via":[164],"multilinguality":[165],"(":[166],"resolves":[167],"same":[169],"multiple":[172],"languages)":[173]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-28T00:00:00"}