{"id":"https://openalex.org/W4414691287","doi":"https://doi.org/10.1109/iccv51701.2025.01964","title":"Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models","display_name":"Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414691287","doi":"https://doi.org/10.1109/iccv51701.2025.01964"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.09209","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiao Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Liang","raw_affiliation_strings":["Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401389","display_name":"Di Wang","orcid":"https://orcid.org/0000-0001-8027-4287"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Wang","raw_affiliation_strings":["Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052716839","display_name":"Zhicheng Jiao","orcid":"https://orcid.org/0000-0002-6968-0919"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhicheng Jiao","raw_affiliation_strings":["Warren Alpert Medical School, Brown University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Warren Alpert Medical School, Brown University,USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059208730","display_name":"Ronghan Li","orcid":"https://orcid.org/0000-0002-1890-7845"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghan Li","raw_affiliation_strings":["Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039054062","display_name":"Pengfei Yang","orcid":"https://orcid.org/0000-0002-5803-8859"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Yang","raw_affiliation_strings":["Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418247","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-6913-8604"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Wang","raw_affiliation_strings":["Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":"21144","last_page":"21154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.78329998254776,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.78329998254776,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.7077000141143799,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.6858000159263611,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.6402000188827515},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6366000175476074},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5918999910354614},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.42489999532699585},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.36309999227523804},{"id":"https://openalex.org/keywords/subject-matter-expert","display_name":"Subject-matter expert","score":0.3621000051498413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7757999897003174},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6402000188827515},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6366000175476074},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5918999910354614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4431999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43880000710487366},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.42489999532699585},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.3621000051498413},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.26510000228881836}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.09209","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.09209","pdf_url":"https://arxiv.org/pdf/2507.09209","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2507.09209","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.09209","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"pmh:oai:arXiv.org:2507.09209","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.09209","pdf_url":"https://arxiv.org/pdf/2507.09209","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1696189465","display_name":null,"funder_award_id":"62302354","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,174],"rapid":[1],"advancements":[2],"in":[3,37,121,184],"Vision":[4,49],"Language":[5,50],"Models":[6],"(VLMs)":[7],"have":[8,23],"prompted":[9],"the":[10,45,131,138,158,177],"development":[11],"of":[12,47,134,179],"multi-modal":[13],"medical":[14,38,151],"assistant":[15],"systems.":[16],"Despite":[17],"this":[18],"progress,":[19],"current":[20],"models":[21,170],"still":[22,72],"inherent":[24],"probabilistic":[25],"uncertainties,":[26],"often":[27],"producing":[28],"erroneous":[29],"or":[30,61],"unverified":[31],"responses-an":[32],"issue":[33],"with":[34,58,76,96,145,161,171],"serious":[35],"implications":[36],"applications.":[39],"Existing":[40],"methods":[41],"aim":[42],"to":[43,93,109,118,129],"enhance":[44],"performance":[46],"Medical":[48],"Model":[51],"(MedVLM)":[52],"by":[53],"adjusting":[54],"model":[55],"structure,":[56],"fine-tuning":[57],"high-quality":[59],"data,":[60],"through":[62],"preference":[63],"fine-tuning.":[64],"However,":[65],"these":[66,81],"training-dependent":[67],"strategies":[68],"are":[69,141],"costly":[70],"and":[71,125,143,164],"lack":[73],"sufficient":[74],"alignment":[75],"clinical":[77,97,188],"expertise.":[78],"To":[79],"address":[80],"issues,":[82],"we":[83],"propose":[84],"an":[85,105],"expert-in-the-loop":[86],"framework":[87,103],"named":[88],"Expert-Controlled":[89],"Classifier-Free":[90],"Guidance":[91],"(Expert-CFG)":[92],"align":[94,144],"MedVLM":[95],"expertise":[98],"without":[99],"additional":[100],"training.":[101],"This":[102],"introduces":[104],"uncertainty":[106],"estimation":[107],"strategy":[108],"identify":[110],"unreliable":[111],"outputs.":[112],"It":[113],"then":[114],"retrieves":[115],"relevant":[116],"references":[117],"assist":[119],"experts":[120],"highlighting":[122],"key":[123],"terms":[124],"applies":[126],"classifier-free":[127],"guidance":[128],"refine":[130],"token":[132],"embeddings":[133],"MedVLM,":[135],"ensuring":[136],"that":[137,157],"adjusted":[139],"outputs":[140],"correct":[142],"expert":[146,166],"highlights.":[147],"Evaluations":[148],"across":[149],"three":[150],"visual":[152],"question":[153],"answering":[154],"benchmarks":[155],"demonstrate":[156,176],"proposed":[159],"Expert-CFG,":[160],"4.2B":[162],"parameters":[163],"limited":[165],"annotations,":[167],"outperforms":[168],"state-of-the-art":[169],"13B":[172],"parameters.":[173],"results":[175],"feasibility":[178],"deploying":[180],"such":[181],"a":[182],"system":[183],"resource-limited":[185],"settings":[186],"for":[187],"use.":[189]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}