{"id":"https://openalex.org/W7160242510","doi":"https://doi.org/10.1109/wacv61042.2026.00097","title":"DermEVAL: A Dermatologist-Reviewed Benchmark for Multimodal Large Language Models","display_name":"DermEVAL: A Dermatologist-Reviewed Benchmark for Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160242510","doi":"https://doi.org/10.1109/wacv61042.2026.00097"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5134796013","display_name":"Hongjin Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Hongjin Zhao","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135340594","display_name":"Weihao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Weihao Li","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025229672","display_name":"Zhenyue Qin","orcid":"https://orcid.org/0000-0002-3471-6280"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhenyue Qin","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001285878","display_name":"Ge-Peng Ji","orcid":"https://orcid.org/0000-0001-7092-2877"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ge-Peng Ji","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135392117","display_name":"Yang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130896088","display_name":"Tom Gedeon","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tom Gedeon","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135327635","display_name":"Nick Barnes","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nick Barnes","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5134796013"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.90341045,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"927","last_page":"937"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10392","display_name":"Cutaneous Melanoma Detection and Management","score":0.301800012588501,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"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/T10392","display_name":"Cutaneous Melanoma Detection and Management","score":0.301800012588501,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"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":0.06889999657869339,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.0568000003695488,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.4537000060081482},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.32820001244544983},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.32359999418258667},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.29030001163482666},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.25}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6692000031471252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.510699987411499},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4034999907016754},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.24719999730587006}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46076104044914246,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1973341111","https://openalex.org/W2044097773","https://openalex.org/W2096203351","https://openalex.org/W2114550641","https://openalex.org/W2980673424","https://openalex.org/W3081168214","https://openalex.org/W3153469116","https://openalex.org/W3188437627","https://openalex.org/W4223899585","https://openalex.org/W4385572239","https://openalex.org/W4388078979","https://openalex.org/W4400362569","https://openalex.org/W4400663251","https://openalex.org/W4402713111","https://openalex.org/W4402727946","https://openalex.org/W4402965924","https://openalex.org/W4403089285","https://openalex.org/W4403778769","https://openalex.org/W4404509535","https://openalex.org/W4404784276","https://openalex.org/W4405427526","https://openalex.org/W4405595839","https://openalex.org/W4411071764","https://openalex.org/W4411113224","https://openalex.org/W7118298638","https://openalex.org/W7133197087","https://openalex.org/W7133205228","https://openalex.org/W7133212838","https://openalex.org/W7160320227"],"related_works":[],"abstract_inverted_index":{"Clinical":[0],"photographs":[1],"play":[2],"a":[3,47,75],"vital":[4],"role":[5],"in":[6,11,38,62,121],"conversational":[7],"computer-aided":[8],"diagnosis,":[9],"particularly":[10],"dermatology.":[12,63],"However,":[13],"existing":[14],"skin":[15,72,138],"disease":[16],"benchmarks":[17],"contain":[18],"limitations":[19],"like":[20],"insufficient":[21],"dataset":[22],"size,":[23],"the":[24,30,54,91,117],"sole":[25],"presence":[26],"of":[27,32,56,77,93,119],"categorical":[28],"labels,":[29],"lack":[31],"expert":[33],"inspections,":[34],"and":[35,88,104,129],"limited":[36],"diversity":[37],"annotations.":[39],"To":[40],"address":[41],"these":[42],"shortcomings,":[43],"we":[44],"introduce":[45],"DermEVAL,":[46],"large-scale":[48],"benchmark":[49,65],"specifically":[50],"designed":[51,109],"to":[52,110],"evaluate":[53,116],"performance":[55,118,156],"Multimodal":[57],"Large":[58],"Language":[59],"Models":[60],"(MLLMs)":[61],"Our":[64,132],"includes":[66],"image-text":[67],"pairs":[68],"depicting":[69],"16":[70],"distinct":[71],"diseases,":[73],"featuring":[74],"total":[76],"11,347":[78],"representative":[79],"images":[80],"drawn":[81],"from":[82],"various":[83],"dermatological":[84],"datasets,":[85],"carefully":[86],"selected":[87],"annotated":[89],"with":[90],"guidance":[92],"dermatologists.":[94],"DermEVAL":[95,152],"enables":[96],"two":[97],"primary":[98],"tasks:":[99],"visual":[100],"question":[101],"answering":[102],"(VQA)":[103],"medical":[105,113],"report":[106],"generation":[107],"(MRG),":[108],"simulate":[111],"real-world":[112],"diagnostics.":[114],"We":[115,145],"MLLMs":[120,150],"dermatology":[122],"using":[123,151],"multiple":[124],"metrics,":[125],"including":[126],"traditional":[127],"metrics":[128],"GPT-4V-based":[130],"assessments.":[131],"results":[133],"indicate":[134],"that":[135,148],"accurately":[136],"diagnosing":[137],"diseases":[139],"remains":[140],"challenging":[141],"for":[142],"state-of-the-art":[143],"MLLMs.":[144],"also":[146],"demonstrate":[147],"fine-tuning":[149],"significantly":[153],"improves":[154],"their":[155],"on":[157],"dermatology-related":[158],"image\u2013text":[159],"tasks.":[160]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2026-05-06T00:00:00"}
