{"id":"https://openalex.org/W7131129852","doi":"https://doi.org/10.1109/iccvw69036.2025.00142","title":"Prompt4Trust: A Reinforcement Learning Prompt Augmentation Framework for Clinically-Aligned Confidence Calibration in Multimodal Large Language Models","display_name":"Prompt4Trust: A Reinforcement Learning Prompt Augmentation Framework for Clinically-Aligned Confidence Calibration in Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131129852","doi":"https://doi.org/10.1109/iccvw69036.2025.00142"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00142","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 Workshops (ICCVW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5115679443","display_name":"Anita Kriz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Anita Kriz","raw_affiliation_strings":["McGill University, Canada Mila - Quebec Artificial Intelligence Institute,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University, Canada Mila - Quebec Artificial Intelligence Institute,Canada","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126618124","display_name":"Elizabeth Laura Janes","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Elizabeth Laura Janes","raw_affiliation_strings":["McGill University, Canada Mila - Quebec Artificial Intelligence Institute,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University, Canada Mila - Quebec Artificial Intelligence Institute,Canada","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126595117","display_name":"Xing Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xing Shen","raw_affiliation_strings":["McGill University, Canada Mila - Quebec Artificial Intelligence Institute,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University, Canada Mila - Quebec Artificial Intelligence Institute,Canada","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tal Arbel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tal Arbel","raw_affiliation_strings":["McGill University, Canada Mila - Quebec Artificial Intelligence Institute,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University, Canada Mila - Quebec Artificial Intelligence Institute,Canada","institution_ids":["https://openalex.org/I4210164802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210164802"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69546409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1331","last_page":"1340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.5411999821662903,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.5411999821662903,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.15289999544620514,"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/T10028","display_name":"Topic Modeling","score":0.12389999628067017,"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/calibration","display_name":"Calibration","score":0.7073000073432922},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6955000162124634},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6410999894142151},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5275999903678894},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4758000075817108},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.44769999384880066},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4323999881744385},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.42730000615119934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821000218391418},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.7073000073432922},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6955000162124634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6482999920845032},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6410999894142151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5921000242233276},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5275999903678894},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.44769999384880066},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4323999881744385},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3937000036239624},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3043999969959259},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00142","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 Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320326644","display_name":"Canada First Research Excellence Fund","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2073241381","https://openalex.org/W2254249950","https://openalex.org/W2971561076","https://openalex.org/W4365143687","https://openalex.org/W4384071683","https://openalex.org/W4384561707","https://openalex.org/W4385573003","https://openalex.org/W4389518686","https://openalex.org/W4394782456","https://openalex.org/W4399803256","https://openalex.org/W4402671289","https://openalex.org/W4402683791","https://openalex.org/W4402713111","https://openalex.org/W4404534210","https://openalex.org/W4405595839","https://openalex.org/W4405673884","https://openalex.org/W4409363988","https://openalex.org/W4411799315"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"large":[1],"language":[2],"models":[3],"(MLLMs)":[4],"hold":[5],"considerable":[6],"promise":[7],"for":[8,81,130,198,217],"applications":[9],"in":[10,15,87,108,192,224],"healthcare.":[11],"However,":[12],"their":[13],"deployment":[14],"safety-critical":[16],"settings":[17],"is":[18,57,68,92,165],"hindered":[19],"by":[20,139],"two":[21],"key":[22],"limitations:":[23],"(i)":[24],"sensitivity":[25],"to":[26,33,49,94,105,189],"prompt":[27,82,215],"design,":[28],"and":[29,132],"(ii)":[30],"a":[31,45,62,101,180],"tendency":[32],"generate":[34,106],"incorrect":[35],"responses":[36,107],"with":[37,179],"high":[38,65],"confidence.":[39],"As":[40],"clinicians":[41],"may":[42],"rely":[43],"on":[44,160],"model's":[46],"stated":[47],"confidence":[48,85,112],"gauge":[50],"the":[51,75,110,161,196,202,209,219,220],"reliability":[52],"of":[53,126,167,211,222],"its":[54],"predictions,":[55],"it":[56,67],"especially":[58],"important":[59],"that":[60,99],"when":[61],"model":[63],"expresses":[64],"confidence,":[66],"also":[69,148],"highly":[70],"accurate.":[71],"We":[72],"introduce":[73],"Prompt4Trust,":[74],"first":[76],"reinforcement":[77],"learning":[78],"(RL)":[79],"framework":[80,177],"augmentation":[83],"targeting":[84],"calibration":[86,120,127,143,200],"MLLMs.":[88],"A":[89],"lightweight":[90],"LLM":[91],"trained":[93,178],"produce":[95],"context-aware":[96],"auxiliary":[97],"prompts":[98],"guide":[100],"downstream":[102,182],"task":[103,150,183],"MLLM":[104,184],"which":[109,164],"expressed":[111],"more":[113],"accurately":[114],"reflects":[115],"predictive":[116],"accuracy.":[117],"Unlike":[118],"conventional":[119],"techniques,":[121],"Prompt4Trust":[122],"specifically":[123],"prioritizes":[124],"aspects":[125],"most":[128],"critical":[129,226],"safe":[131],"trustworthy":[133],"clinical":[134],"decisionmaking.":[135],"Beyond":[136],"improvements":[137],"driven":[138],"this":[140],"clinically":[141],"motivated":[142],"objective,":[144],"our":[145,176,193],"proposed":[146],"method":[147],"improves":[149],"accuracy,":[151],"achieving":[152],"state-of-the-art":[153],"medical":[154,172],"visual":[155],"question":[156],"answering":[157],"(VQA)":[158],"performance":[159],"PMC-VQA":[162],"benchmark,":[163],"composed":[166],"multiple-choice":[168],"questions":[169],"spanning":[170],"diverse":[171],"imaging":[173],"modalities.":[174],"Moreover,":[175],"small":[181],"showed":[185],"promising":[186],"zero-shot":[187],"generalization":[188],"larger":[190],"MLLMs":[191,223],"experiments,":[194],"suggesting":[195],"potential":[197,210],"scalable":[199],"without":[201],"associated":[203],"computational":[204],"costs.":[205],"This":[206],"work":[207],"demonstrates":[208],"automated":[212],"yet":[213],"human-aligned":[214],"engineering":[216],"improving":[218],"trustworthiness":[221],"safety":[225],"settings.":[227],"Our":[228],"codebase":[229],"can":[230],"be":[231],"found":[232],"at":[233],"https://github.com/xingbpshen/prompt4trust.":[234]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-24T00:00:00"}