{"id":"https://openalex.org/W7128728355","doi":"https://doi.org/10.48448/cr5d-s546","title":"MultiMedBench: A Scenario-Aware Benchmark for Evaluating Knowledge Editing in Medical VQA","display_name":"MultiMedBench: A Scenario-Aware Benchmark for Evaluating Knowledge Editing in Medical VQA","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7128728355","doi":"https://doi.org/10.48448/cr5d-s546"},"language":"en","primary_location":{"id":"doi:10.48448/cr5d-s546","doi":"https://doi.org/10.48448/cr5d-s546","is_oa":true,"landing_page_url":"https://doi.org/10.48448/cr5d-s546","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"volume":null,"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/cr5d-s546","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125741655","display_name":"Association for Artificial Intelligence 2026","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Artificial Intelligence 2026","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125744984","display_name":"Haodong Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Haodong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125729887","display_name":"Xiang Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110659409","display_name":"Sheng-Jun Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Sheng-Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125686179","display_name":"Dong Liang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125712860","display_name":"Zhongying Pan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Zhongying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158937391","display_name":"Bo Qian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125717148","display_name":"Yu Tian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125716457","display_name":"Yadong Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yadong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112950235","display_name":"Shengtao Wen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Shengtao","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8701000213623047,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8701000213623047,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.09870000183582306,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.007499999832361937,"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/knowledge-editing","display_name":"knowledge editing","score":0.996999979019165},{"id":"https://openalex.org/keywords/medical-visual-question-answering","display_name":"medical visual question answering","score":0.8629999756813049},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.7789999842643738},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8579999804496765},{"id":"https://openalex.org/keywords/lifelong-learning","display_name":"lifelong learning","score":0.5709999799728394},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"visual reasoning","score":0.5590000152587891},{"id":"https://openalex.org/keywords/clinical-decision-support","display_name":"clinical decision support","score":0.6830000281333923},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.5059999823570251},{"id":"https://openalex.org/keywords/memory-usage","display_name":"memory usage","score":0.6980000138282776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7795000076293945},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.7265999913215637},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6686000227928162},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5637000203132629},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5525000095367432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5188000202178955},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45190000534057617},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4124000072479248},{"id":"https://openalex.org/C2985722590","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medical knowledge","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30799999833106995},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2847999930381775},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/cr5d-s546","doi":"https://doi.org/10.48448/cr5d-s546","is_oa":true,"landing_page_url":"https://doi.org/10.48448/cr5d-s546","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/cr5d-s546","doi":"https://doi.org/10.48448/cr5d-s546","is_oa":true,"landing_page_url":"https://doi.org/10.48448/cr5d-s546","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7128705392","https://openalex.org/W4416181018","https://openalex.org/W6910641916","https://openalex.org/W7155368989","https://openalex.org/W4416149845","https://openalex.org/W7082251813","https://openalex.org/W7167589897","https://openalex.org/W4416035534","https://openalex.org/W4404648428","https://openalex.org/W7162750084"],"abstract_inverted_index":{"Knowledge":[0],"editing":[1,172],"(KE)":[2],"provides":[3,163],"a":[4,89,164],"scalable":[5],"approach":[6],"for":[7,167],"updating":[8],"factual":[9],"knowledge":[10,50,171],"in":[11,24,38,75,127,145,174],"large":[12],"language":[13],"models":[14],"without":[15],"full":[16],"retraining.":[17],"While":[18],"previous":[19],"studies":[20],"have":[21],"demonstrated":[22],"effectiveness":[23],"general":[25,102],"domains":[26],"and":[27,57,84,95,97,103,112,123],"medical":[28,40,45],"QA":[29],"tasks,":[30],"little":[31],"attention":[32],"has":[33],"been":[34],"paid":[35],"to":[36,54,72],"KE":[37,46,74,149],"multimodal":[39,77],"scenarios.":[41],"Unlike":[42],"text-only":[43],"settings,":[44],"demands":[47],"integrating":[48],"updated":[49],"with":[51,121],"visual":[52],"reasoning":[53,85],"support":[55],"safe":[56],"interpretable":[58],"clinical":[59,76,129],"decisions.":[60],"To":[61],"address":[62],"this":[63],"gap,":[64],"we":[65],"propose":[66],"MultiMedBench,":[67],"the":[68,156,175],"first":[69],"benchmark":[70],"tailored":[71],"evaluating":[73],"tasks.":[78],"Our":[79],"framework":[80],"spans":[81],"both":[82],"understanding":[83],"task":[86],"types,":[87],"defines":[88],"three-dimensional":[90],"metric":[91],"suite":[92],"(reliability,":[93],"generality,":[94],"locality),":[96],"supports":[98],"cross-paradigm":[99],"comparisons":[100],"across":[101,148],"domain-specific":[104],"models.":[105],"We":[106,131],"conduct":[107],"extensive":[108],"experiments":[109],"under":[110],"single-editing":[111],"lifelong-editing":[113],"settings.":[114],"Results":[115],"suggest":[116],"that":[117],"current":[118,159],"methods":[119],"struggle":[120],"generalization":[122],"long-tail":[124],"reasoning,":[125],"particularly":[126],"complex":[128],"workflows.":[130],"further":[132],"present":[133],"an":[134],"efficiency":[135],"analysis":[136],"(e.g.,":[137],"edit":[138],"latency,":[139],"memory":[140],"footprint),":[141],"revealing":[142],"practical":[143],"trade-offs":[144],"real-world":[146],"deployment":[147],"paradigms.":[150],"Overall,":[151],"MultiMedBench":[152],"not":[153],"only":[154],"reveals":[155],"limitations":[157],"of":[158],"approaches":[160],"but":[161],"also":[162],"solid":[165],"foundation":[166],"developing":[168],"clinically":[169],"robust":[170],"techniques":[173],"future.":[176]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-13T00:00:00"}