{"id":"https://openalex.org/W7131415284","doi":"https://doi.org/10.48550/arxiv.2602.19024","title":"Towards Calibrating Prompt Tuning of Vision-Language Models","display_name":"Towards Calibrating Prompt Tuning of Vision-Language Models","publication_year":2026,"publication_date":"2026-02-22","ids":{"openalex":"https://openalex.org/W7131415284","doi":"https://doi.org/10.48550/arxiv.2602.19024"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.19024","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19024","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.19024","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119282063","display_name":"Ashshak Sharifdeen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sharifdeen, Ashshak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033921097","display_name":"Fahad Shamshad","orcid":"https://orcid.org/0000-0003-2442-0475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shamshad, Fahad","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037593408","display_name":"Muhammad Akhtar Munir","orcid":"https://orcid.org/0000-0002-9642-0936"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Munir, Muhammad Akhtar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007268230","display_name":"Abhishek Basu","orcid":"https://orcid.org/0000-0003-4167-3722"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Basu, Abhishek","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308431","display_name":"Mohamed Insaf Ismithdeen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ismithdeen, Mohamed Insaf","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126659429","display_name":"Jeyapriyan Jeyamohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeyamohan, Jeyapriyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045647682","display_name":"Chathurika Sewwandi Silva","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Silva, Chathurika Sewwandi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059676452","display_name":"Karthik Nandakumar","orcid":"https://orcid.org/0000-0002-6274-9725"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nandakumar, Karthik","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126844617","display_name":"Dr Muhammad Asif Khan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Muhammad Haris","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5119282063"],"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":0.9488999843597412,"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":0.9488999843597412,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.009700000286102295,"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":0.006300000008195639,"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":0.7465999722480774},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7125999927520752},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5741999745368958},{"id":"https://openalex.org/keywords/overconfidence-effect","display_name":"Overconfidence effect","score":0.5297999978065491},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5163999795913696},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5042999982833862},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.3734000027179718},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.33219999074935913}],"concepts":[{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.7465999722480774},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7125999927520752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6686999797821045},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5741999745368958},{"id":"https://openalex.org/C51110983","wikidata":"https://www.wikidata.org/wiki/Q16503490","display_name":"Overconfidence effect","level":2,"score":0.5297999978065491},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5042999982833862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4293999969959259},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3928000032901764},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29319998621940613},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2671999931335449},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.19024","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19024","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.19024","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19024","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Prompt":[0],"tuning":[1],"of":[2,46,104],"large-scale":[3],"vision-language":[4],"models":[5],"such":[6],"as":[7],"CLIP":[8,49,111],"enables":[9],"efficient":[10],"task":[11],"adaptation":[12],"without":[13],"updating":[14],"model":[15],"weights.":[16],"However,":[17],"it":[18],"often":[19],"leads":[20],"to":[21,143],"poor":[22],"confidence":[23],"calibration":[24,36,145],"and":[25,88,91,101,126,150],"unreliable":[26],"predictive":[27,40],"uncertainty.":[28],"We":[29],"address":[30],"this":[31],"problem":[32],"by":[33,79],"proposing":[34],"a":[35,70,93],"framework":[37],"that":[38,74,97,132],"enhances":[39],"reliability":[41],"while":[42,83],"preserving":[43,113],"the":[44,47,61,99,137],"geometry":[45],"pretrained":[48],"embedding":[50],"space,":[51],"which":[52],"is":[53],"required":[54],"for":[55,117],"robust":[56],"generalization.":[57,118],"Our":[58],"approach":[59,134],"extends":[60],"standard":[62],"cross-entropy":[63],"loss":[64,96],"with":[65,108],"two":[66],"complementary":[67],"regularizers:":[68],"(1)":[69],"mean-variance":[71],"margin":[72],"penalty":[73],"stabilizes":[75],"inter-class":[76],"logit":[77],"margins":[78],"maximizing":[80],"their":[81,109],"average":[82],"minimizing":[84],"dispersion,":[85],"mitigating":[86],"underconfidence":[87],"overconfidence":[89],"spikes;":[90],"(2)":[92],"text":[94,106],"moment-matching":[95],"aligns":[98],"first":[100],"second":[102],"moments":[103],"tuned":[105],"embeddings":[107],"frozen":[110],"counterparts,":[112],"semantic":[114],"dispersion":[115],"crucial":[116],"Through":[119],"extensive":[120],"experiments":[121],"across":[122],"7":[123],"prompt-tuning":[124],"methods":[125],"11":[127],"diverse":[128],"datasets,":[129],"we":[130],"demonstrate":[131],"our":[133],"significantly":[135],"reduces":[136],"Expected":[138],"Calibration":[139],"Error":[140],"(ECE)":[141],"compared":[142],"competitive":[144],"techniques":[146],"on":[147],"both":[148],"base":[149],"novel":[151],"classes":[152]},"counts_by_year":[],"updated_date":"2026-02-26T06:34:08.959763","created_date":"2026-02-26T00:00:00"}