{"id":"https://openalex.org/W7160230704","doi":"https://doi.org/10.1109/wacv61042.2026.00127","title":"CAAC: Confidence-Aware Attention Calibration to Reduce Hallucinations in Large Vision-Language Models","display_name":"CAAC: Confidence-Aware Attention Calibration to Reduce Hallucinations in Large Vision-Language Models","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160230704","doi":"https://doi.org/10.1109/wacv61042.2026.00127"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00127","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":"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/A5070284255","display_name":"Mehrdad Fazli","orcid":null},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehrdad Fazli","raw_affiliation_strings":["George Mason University,Department of Computer Science,Fairfax,VA,USA,22030"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Mason University,Department of Computer Science,Fairfax,VA,USA,22030","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135396197","display_name":"Bowen Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bowen Wei","raw_affiliation_strings":["George Mason University,Department of Computer Science,Fairfax,VA,USA,22030"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Mason University,Department of Computer Science,Fairfax,VA,USA,22030","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108023630","display_name":"Ahmet Sar\u0131","orcid":"https://orcid.org/0000-0002-7452-083X"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmet Sari","raw_affiliation_strings":["George Mason University,Department of Computer Science,Fairfax,VA,USA,22030"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Mason University,Department of Computer Science,Fairfax,VA,USA,22030","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135392582","display_name":"Ziwei Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziwei Zhu","raw_affiliation_strings":["George Mason University,Department of Computer Science,Fairfax,VA,USA,22030"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Mason University,Department of Computer Science,Fairfax,VA,USA,22030","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44861155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1242","last_page":"1251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.3280999958515167,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.3280999958515167,"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/T13397","display_name":"Hallucinations in medical conditions","score":0.056299999356269836,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.03750000149011612,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6025000214576721},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.35409998893737793},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.24570000171661377},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.23639999330043793}],"concepts":[{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6025000214576721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49869999289512634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4422000050544739},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.35409998893737793},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24570000171661377},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.23639999330043793},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2282000035047531},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.22529999911785126},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.21850000321865082}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00127","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.43019747734069824}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2962735233","https://openalex.org/W4230405732","https://openalex.org/W4385571645","https://openalex.org/W4385801138","https://openalex.org/W4386076522","https://openalex.org/W4389523832","https://openalex.org/W4393160204","https://openalex.org/W4402704633","https://openalex.org/W4402713111","https://openalex.org/W4402726945","https://openalex.org/W4402726948","https://openalex.org/W4402727851","https://openalex.org/W4402753774","https://openalex.org/W4404199641","https://openalex.org/W4404509535","https://openalex.org/W4404682098","https://openalex.org/W4404783118","https://openalex.org/W4404783238","https://openalex.org/W4404788931","https://openalex.org/W4409716856","https://openalex.org/W4409917592","https://openalex.org/W4412888840","https://openalex.org/W4413156530","https://openalex.org/W7133193597","https://openalex.org/W7133220561","https://openalex.org/W7133239970"],"related_works":[],"abstract_inverted_index":{"Large":[0],"vision-language":[1],"models":[2],"(LVLMs)":[3],"achieve":[4],"impressive":[5],"performance":[6],"on":[7,117],"multimodal":[8],"tasks":[9],"but":[10],"often":[11],"suffer":[12],"from":[13,72],"hallucination":[14],"and":[15,35,66,93,120,136],"confidently":[16],"describe":[17],"objects":[18],"or":[19],"attributes":[20],"not":[21],"present":[22],"in":[23,33,129],"the":[24,41,104],"image.":[25],"Current":[26],"training-free":[27],"interventions":[28],"struggle":[29],"to":[30,47,74,87,98],"maintain":[31],"accuracy":[32],"open-ended":[34],"long-form":[36,130],"generation":[37],"scenarios.":[38],"We":[39],"introduce":[40],"Confidence-Aware":[42],"Attention":[43,95],"Calibration":[44,85],"(CAAC)":[45],"framework":[46],"address":[48],"this":[49],"challenge":[50],"by":[51,103],"targeting":[52],"two":[53],"key":[54],"biases:":[55],"spatial":[56],"perception":[57],"bias,":[58,68],"which":[59,69],"distributes":[60],"attention":[61,89],"disproportionately":[62],"across":[63,90],"image":[64],"tokens,":[65,92],"modality":[67],"shifts":[70],"focus":[71],"visual":[73,91,100,112],"textual":[75],"inputs":[76],"over":[77],"time.":[78],"CAAC":[79,125],"employs":[80],"a":[81],"two-step":[82],"approach:":[83],"Visual-Token":[84],"(VTC)":[86],"balance":[88],"Adaptive":[94],"Re-Scaling":[96],"(AAR)":[97],"reinforce":[99],"grounding":[101],"guided":[102],"model\u2019s":[105],"confidence.":[106],"This":[107],"confidence-driven":[108],"adjustment":[109],"ensures":[110],"consistent":[111],"alignment":[113],"during":[114],"generation.":[115],"Experiments":[116],"CHAIR,":[118],"AMBER,":[119],"POPE":[121],"benchmarks":[122],"demonstrate":[123],"that":[124],"outperforms":[126],"baselines,":[127],"particularly":[128],"generations,":[131],"effectively":[132],"reducing":[133],"hallucination.":[134],"Data":[135],"code":[137],"are":[138],"available":[139],"at":[140],"https://github.com/mehrdadfazli/CAAC/.":[141]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}