{"id":"https://openalex.org/W7126026291","doi":"https://doi.org/10.1109/bibm66473.2025.11356537","title":"MoCA-Dialog: A Benchmark for Fine-Grained Evaluation of Large Language Models in Clinical Cognitive Assessment Dialogues","display_name":"MoCA-Dialog: A Benchmark for Fine-Grained Evaluation of Large Language Models in Clinical Cognitive Assessment Dialogues","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126026291","doi":"https://doi.org/10.1109/bibm66473.2025.11356537"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124291148","display_name":"Yunjia Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I905225518","display_name":"Shanghai University of International Business and Economics","ror":"https://ror.org/031t68441","country_code":"CN","type":"education","lineage":["https://openalex.org/I905225518"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yunjia Zhang","raw_affiliation_strings":["Shanghai University of International Business and Economics,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai University of International Business and Economics,Shanghai,China","institution_ids":["https://openalex.org/I905225518"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102619348","display_name":"Junyi Zhu","orcid":"https://orcid.org/0009-0000-7781-0034"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyi Zhu","raw_affiliation_strings":["East China University of Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"East China University of Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124165922","display_name":"Rui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I905225518","display_name":"Shanghai University of International Business and Economics","ror":"https://ror.org/031t68441","country_code":"CN","type":"education","lineage":["https://openalex.org/I905225518"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Shanghai University of International Business and Economics,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai University of International Business and Economics,Shanghai,China","institution_ids":["https://openalex.org/I905225518"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124159280","display_name":"Tianai Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianai Zhuang","raw_affiliation_strings":["East China Normal University,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004094994","display_name":"Jinqiu Sang","orcid":"https://orcid.org/0000-0002-4368-8787"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinqiu Sang","raw_affiliation_strings":["East China Normal University,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123766502","display_name":"HaKyung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"HaKyung Kim","raw_affiliation_strings":["Cognitive Science and Allied Health School, Institute of Life and Health Sciences,Key Laboratory of Language and Cognitive Science (Ministry of Education), Beijing Language and Culture University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Cognitive Science and Allied Health School, Institute of Life and Health Sciences,Key Laboratory of Language and Cognitive Science (Ministry of Education), Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5124291148"],"corresponding_institution_ids":["https://openalex.org/I905225518"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68359654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6654","last_page":"6659"},"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":0.5651000142097473,"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":0.5651000142097473,"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":0.09690000116825104,"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":0.054999999701976776,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8022000193595886},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.6812999844551086},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.45680001378059387},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45080000162124634},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4397999942302704}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8022000193595886},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.6812999844551086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5514000058174133},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45080000162124634},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.414000004529953},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36169999837875366},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3465999960899353},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C161407221","wikidata":"https://www.wikidata.org/wiki/Q4382939","display_name":"Cognitive model","level":3,"score":0.3077000081539154},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2583000063896179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8056532144546509}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2165758561","https://openalex.org/W2970482702","https://openalex.org/W3162922479","https://openalex.org/W4392193048"],"related_works":[],"abstract_inverted_index":{"Current":[0],"benchmarks":[1],"for":[2,65,88,157],"evaluating":[3],"large":[4],"language":[5],"models":[6,108],"(LLMs)":[7],"in":[8,28,117,144],"medicine":[9],"primarily":[10],"focus":[11],"on":[12,170],"static":[13],"questionanswering,":[14],"neglecting":[15],"the":[16,55,66,159],"dynamic,":[17],"interactive":[18],"nature":[19],"of":[20,75,99,162],"many":[21],"clinical":[22,84,160],"workflows.":[23],"This":[24],"is":[25],"particularly":[26],"evident":[27],"cognitive":[29,80,94],"assessments,":[30],"where":[31],"nuanced":[32,146],"dialogue":[33],"and":[34,83,122,148,164,175,188],"multimodal":[35,58,101],"interpretation":[36],"are":[37],"critical,":[38],"yet":[39],"no":[40],"specialized":[41],"benchmark":[42,59,72],"exists":[43],"to":[44],"evaluate":[45],"these":[46,133],"capabilities.":[47],"To":[48],"address":[49],"this":[50],"gap,":[51],"we":[52],"introduce":[53],"MoCADialog,":[54],"first":[56],"large-scale,":[57],"featuring":[60],"5000":[61],"high-fidelity":[62],"simulated":[63],"dialogues":[64],"Montreal":[67],"Cognitive":[68],"Assessment":[69],"(MoCA).":[70],"The":[71],"includes":[73],"tasks":[74],"increasing":[76],"complexity:":[77],"accurate":[78],"scoring,":[79],"profile":[81],"generation,":[82],"error":[85,128],"attribution,":[86],"allowing":[87],"a":[89,154],"fine-grained":[90],"evaluation":[91,98],"across":[92],"seven":[93],"domains.":[95],"Our":[96],"comprehensive":[97],"state-of-the-art":[100],"LLMs":[102,163],"reveals":[103],"significant":[104],"performance":[105],"disparities;":[106],"while":[107],"excel":[109],"at":[110,191],"simple":[111],"recall":[112],"tasks,":[113],"they":[114],"consistently":[115],"fail":[116],"domains":[118],"requiring":[119],"executive":[120],"function":[121],"abstract":[123],"reasoning.":[124,151],"A":[125],"novel,":[126],"clinically-driven":[127],"analysis":[129],"further":[130],"indicates":[131],"that":[132,166],"failures":[134],"stem":[135],"not":[136,178],"from":[137,141],"knowledge":[138,182],"deficits,":[139],"but":[140],"fundamental":[142],"difficulties":[143],"interpreting":[145],"cues":[147],"applying":[149],"domain-specific":[150],"MoCA-Dialog":[152],"provides":[153],"crucial":[155],"tool":[156],"assessing":[158],"readiness":[161],"highlights":[165],"future":[167],"progress":[168],"depends":[169],"enhancing":[171],"their":[172,181],"core":[173],"reasoning":[174],"interpretive":[176],"abilities,":[177],"just":[179],"expanding":[180],"base.":[183],"We":[184],"release":[185],"our":[186],"demo,":[187],"prompt":[189],"examples":[190],"https://mocadialogue.github.io.":[192]},"counts_by_year":[],"updated_date":"2026-02-01T03:34:12.195049","created_date":"2026-01-30T00:00:00"}