{"id":"https://openalex.org/W4414908435","doi":"https://doi.org/10.1109/tcsvt.2025.3618949","title":"Asking Questions to Alleviate Object Hallucination in Large Vision-Language Models","display_name":"Asking Questions to Alleviate Object Hallucination in Large Vision-Language Models","publication_year":2025,"publication_date":"2025-10-07","ids":{"openalex":"https://openalex.org/W4414908435","doi":"https://doi.org/10.1109/tcsvt.2025.3618949"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3618949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3618949","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","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":null,"display_name":"Chao Bi","orcid":"https://orcid.org/0000-0001-5895-1202"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Bi","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","Institute of Computing Technology, Key Laboratory of Intelligent Information Processing, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5895-1202","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Computing Technology, Key Laboratory of Intelligent Information Processing, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005205981","display_name":"Tiantian Dang","orcid":"https://orcid.org/0009-0000-6653-6893"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiantian Dang","raw_affiliation_strings":["School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669242","display_name":"Shuhui Wang","orcid":"https://orcid.org/0000-0002-5931-0527"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhui Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","Institute of Computing Technology, Key Laboratory of Intelligent Information Processing, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5931-0527","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Computing Technology, Key Laboratory of Intelligent Information Processing, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657103","display_name":"Feng Cao","orcid":"https://orcid.org/0000-0002-1294-2463"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Cao","raw_affiliation_strings":["School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Jinan, Shandong, China","School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Jinan, Shandong, China","institution_ids":["https://openalex.org/I152269853"]},{"raw_affiliation_string":"School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Shandong, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","Institute of Computing Technology, Key Laboratory of Intelligent Information Processing, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7542-296X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Computing Technology, Key Laboratory of Intelligent Information Processing, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8671,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77261902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"36","issue":"3","first_page":"3497","last_page":"3512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10094","display_name":"Epilepsy research and treatment","score":0.885200023651123,"subfield":{"id":"https://openalex.org/subfields/2738","display_name":"Psychiatry and Mental health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10094","display_name":"Epilepsy research and treatment","score":0.885200023651123,"subfield":{"id":"https://openalex.org/subfields/2738","display_name":"Psychiatry and Mental health"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.8395000100135803,"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/T11094","display_name":"Face Recognition and Perception","score":0.8034999966621399,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7538999915122986},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6384999752044678},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6165000200271606},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.5519000291824341},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5284000039100647},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.47380000352859497},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47360000014305115},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.42309999465942383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766000032424927},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7538999915122986},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6384999752044678},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6165000200271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6154999732971191},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.5519000291824341},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5284000039100647},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47360000014305115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45820000767707825},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4178999960422516},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3118000030517578},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2768000066280365},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3618949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3618949","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1619870141","display_name":null,"funder_award_id":"2023YFC2508704","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3840657713","display_name":null,"funder_award_id":"62441232","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4199693610","display_name":null,"funder_award_id":"62236008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6212863906","display_name":null,"funder_award_id":"U21B2038","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2904565150","https://openalex.org/W2962735233","https://openalex.org/W2963260436","https://openalex.org/W2963323070","https://openalex.org/W2963518342","https://openalex.org/W2966162142","https://openalex.org/W3006871679","https://openalex.org/W3034383590","https://openalex.org/W3035512383","https://openalex.org/W3047995861","https://openalex.org/W3107593830","https://openalex.org/W3111278072","https://openalex.org/W3136792391","https://openalex.org/W3169283738","https://openalex.org/W3177934633","https://openalex.org/W3201174429","https://openalex.org/W3214007456","https://openalex.org/W4206982465","https://openalex.org/W4308713560","https://openalex.org/W4309674289","https://openalex.org/W4312341105","https://openalex.org/W4312846625","https://openalex.org/W4323338702","https://openalex.org/W4383889937","https://openalex.org/W4385569922","https://openalex.org/W4386065691","https://openalex.org/W4386075985","https://openalex.org/W4386699374","https://openalex.org/W4386848004","https://openalex.org/W4387010079","https://openalex.org/W4387831730","https://openalex.org/W4389160105","https://openalex.org/W4389518784","https://openalex.org/W4389519598","https://openalex.org/W4389520252","https://openalex.org/W4389523832","https://openalex.org/W4389524413","https://openalex.org/W4389610068","https://openalex.org/W4390590848","https://openalex.org/W4390659080","https://openalex.org/W4390874324","https://openalex.org/W4393149022","https://openalex.org/W4393160204","https://openalex.org/W4399803256","https://openalex.org/W4401042446","https://openalex.org/W4401042773","https://openalex.org/W4401042962","https://openalex.org/W4402703109","https://openalex.org/W4402727851","https://openalex.org/W4402753774","https://openalex.org/W4402754134","https://openalex.org/W4403791995","https://openalex.org/W4404534210","https://openalex.org/W4404782092","https://openalex.org/W4405596328","https://openalex.org/W4409348240","https://openalex.org/W4412158322","https://openalex.org/W7133193597","https://openalex.org/W7133204206","https://openalex.org/W7133220561"],"related_works":[],"abstract_inverted_index":{"Large":[0],"vision":[1],"language":[2,13],"models":[3,14],"(LVLMs)":[4],"have":[5],"achieved":[6],"rapid":[7],"development.":[8],"However,":[9],"just":[10],"like":[11],"large":[12,193],"(LLMs),":[15],"LVLMs":[16,158,218,285],"face":[17],"the":[18,26,29,37,57,87,127,135,139,142,151,155,172,182,187,204,221,232,240,260],"critical":[19],"challenge":[20],"of":[21,36,46,157,174,224,234],"hallucination,":[22],"which":[23],"refers":[24],"to":[25,53,82,108,125,141,146,150,153,219],"phenomenon":[27],"that":[28,70,170],"generation":[30,58,190,227],"text":[31,226],"containing":[32],"references":[33],"or":[34,42],"descriptions":[35],"input":[38],"image":[39],"is":[40,275,292],"incorrect":[41],"inconsistent.":[43],"The":[44,290],"causes":[45],"hallucinations":[47,110],"are":[48,144],"complex":[49],"and":[50,96,116,130,181,192,255,263,278],"therefore":[51],"difficult":[52],"avoid":[54],"directly":[55,202],"during":[56,86,159],"process.":[59,89],"To":[60,161],"alleviate":[61,109],"hallucinations,":[62],"existing":[63],"studies":[64],"mainly":[65],"employ":[66],"an":[67,167],"instruction-tuning":[68],"approach":[69],"requires":[71],"model":[72,177,191],"retraining":[73],"with":[74],"specific":[75,84],"data.":[76],"Other":[77],"methods":[78],"use":[79],"decoding":[80,88],"constraints":[81],"penalize":[83],"tokens":[85],"These":[90],"will":[91,207],"incur":[92],"expensive":[93],"annotation":[94],"costs":[95,267],"computation":[97],"burden.":[98],"In":[99],"this":[100,163],"paper,":[101],"we":[102,165],"propose":[103],"a":[104,175,210],"framework":[105,185],"named":[106],"AQAH":[107,120,199,235],"without":[111],"relying":[112],"on":[113],"manual":[114],"data":[115],"large-scale":[117],"parameter":[118],"tuning.":[119],"compares":[121],"multiple":[122],"generated":[123],"samples":[124],"locate":[126],"hallucination":[128,156,237,270],"factors,":[129],"then":[131],"asks":[132],"questions":[133,143],"about":[134],"uncertain":[136],"information.":[137],"Finally,":[138],"answers":[140],"used":[145],"add":[147],"auxiliary":[148],"information":[149],"prompt":[152],"correct":[154],"regeneration.":[160],"facilitate":[162],"process,":[164],"constructed":[166],"automatic":[168],"process":[169],"involves":[171],"training":[173],"small":[176,188],"for":[178],"question":[179,189,194,257],"generation,":[180],"agent":[183],"collaboration":[184],"including":[186],"answering":[195],"foundation":[196],"model.":[197],"Since":[198],"does":[200],"not":[201,208],"constrain":[203],"decoding,":[205],"it":[206],"cause":[209],"significant":[211],"degradation":[212],"in":[213,236,248,283],"inference":[214],"efficiency,":[215],"nor":[216],"force":[217],"suffer":[220],"notorious":[222],"problem":[223],"shortened":[225],"length.":[228],"We":[229],"experimentally":[230],"demonstrate":[231],"effectiveness":[233],"alleviation":[238],"through":[239],"proposed":[241],"\u201cactive":[242],"questioning":[243],"&":[244],"answer":[245],"verification\u201d":[246],"paradigm":[247],"various":[249],"multimodal":[250],"tasks":[251],"such":[252],"as":[253],"captioning":[254],"visual":[256],"answering.":[258],"Beyond":[259],"promising":[261],"performance":[262],"fewer":[264],"training/inference":[265],"time":[266],"against":[268],"other":[269],"reduction":[271],"methods,":[272],"our":[273],"method":[274],"highly":[276],"interpretable":[277],"flexible,":[279],"showing":[280],"great":[281],"potential":[282],"improving":[284],"by":[286],"exploiting":[287],"small-scale":[288],"models.":[289],"code":[291],"available":[293],"at":[294],"https://github.com/bcxbg/AQAH.":[295]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}