{"id":"https://openalex.org/W7138110279","doi":"https://doi.org/10.1609/aaai.v40i8.37594","title":"Analyzing and Mitigating Object Hallucination: A Training Bias Perspective","display_name":"Analyzing and Mitigating Object Hallucination: A Training Bias Perspective","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138110279","doi":"https://doi.org/10.1609/aaai.v40i8.37594"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i8.37594","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37594","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i8.37594","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129676975","display_name":"Yifan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yifan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129690435","display_name":"Kun Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030667310","display_name":"Xin Zhao","orcid":"https://orcid.org/0000-0002-1801-4393"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129740972","display_name":"Lei Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125635347","display_name":"Jirong Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jirong Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5129676975"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29148835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"8","first_page":"6636","last_page":"6643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.4131999909877777,"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":0.4131999909877777,"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/T11094","display_name":"Face Recognition and Perception","score":0.07320000231266022,"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/T13397","display_name":"Hallucinations in medical conditions","score":0.060600001364946365,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.7153000235557556},{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.6955999732017517},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6187999844551086},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6107000112533569},{"id":"https://openalex.org/keywords/data-driven","display_name":"Data-driven","score":0.46389999985694885},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43529999256134033},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4205999970436096},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4090000092983246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7174999713897705},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.7153000235557556},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.6955999732017517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6385999917984009},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6187999844551086},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6107000112533569},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.598800003528595},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.46389999985694885},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.35740000009536743},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.33820000290870667},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32030001282691956},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i8.37594","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37594","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37594","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i8.37594","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37594","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.727020263671875}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"scaling":[1],"up":[2],"training":[3,43,61,81,89,132,173,188,221,255],"data":[4,44,62,90,189,222,256],"has":[5],"significantly":[6,231],"improved":[7],"the":[8,21,30,40,60,125,138,178,187,206,212,220,228],"general":[9],"multimodal":[10],"capabilities":[11],"of":[12,42,55,63,214,227],"Large":[13],"Vision-Language":[14],"Models":[15],"(LVLMs),":[16],"they":[17,83,101],"still":[18],"suffer":[19,79],"from":[20,59,80],"hallucination":[22,171,233,263],"issue,":[23,119],"generating":[24],"text":[25],"that":[26,76,130,203],"is":[27,134],"inconsistent":[28],"with":[29,65,245],"visual":[31,149],"input.":[32],"This":[33],"phenomenon":[34],"motivates":[35],"us":[36],"to":[37,85,111,145,168,247,252,262],"systematically":[38],"investigate":[39],"role":[41],"in":[45,137],"hallucination.":[46,267],"We":[47],"introduce":[48],"a":[49,191,197],"new":[50],"benchmark,":[51],"POPEv2,":[52,73],"which":[53,143],"consists":[54],"counterfactual":[56,105],"images":[57,96],"collected":[58],"LVLMs":[64,78],"certain":[66],"objects":[67],"masked.":[68],"Through":[69],"comprehensive":[70],"evaluation":[71],"on":[72,95,104,124,155,186],"we":[74,120,158],"find":[75],"current":[77],"bias:":[82],"fail":[84],"fully":[86],"leverage":[87],"their":[88],"and":[91,163,183,195,199,223,237,254,258],"hallucinate":[92],"more":[93],"frequently":[94],"seen":[97],"during":[98],"training.":[99],"Specifically,":[100],"perform":[102],"poorly":[103],"images,":[106],"often":[107],"incorrectly":[108],"answering":[109],"\u201cYes\u201d":[110],"questions":[112],"about":[113],"masked":[114],"objects.":[115],"To":[116],"understand":[117],"this":[118,131],"conduct":[121],"probing":[122],"experiments":[123,210],"models\u2019":[126],"internal":[127],"components,":[128],"revealing":[129],"bias":[133,174,194],"primarily":[135],"located":[136],"language":[139],"modeling":[140],"(LM)":[141],"head,":[142],"fails":[144],"correctly":[146],"translate":[147],"accurate":[148],"representations":[150],"into":[151],"textual":[152],"outputs.":[153],"Based":[154],"these":[156],"findings,":[157],"propose":[159],"Obliviate,":[160],"an":[161],"efficient":[162],"lightweight":[164],"unlearning":[165],"method":[166],"designed":[167],"mitigate":[169],"object":[170],"via":[172],"unlearning.":[175],"Obliviate":[176,230],"identifies":[177],"discrepancy":[179],"between":[180],"ground-truth":[181],"labels":[182],"model":[184,249],"outputs":[185],"as":[190],"proxy":[192],"for":[193],"adopts":[196],"parameter-":[198],"data-efficient":[200],"fine-tuning":[201],"strategy":[202],"only":[204,218],"updates":[205],"LM":[207],"head.":[208],"Extensive":[209],"demonstrate":[211],"effectiveness":[213],"our":[215],"approach.":[216],"While":[217],"reusing":[219],"updating":[224],"approximately":[225],"2%":[226],"parameters,":[229],"reduces":[232],"across":[234],"both":[235,248],"discriminative":[236],"generative":[238],"tasks.":[239],"Furthermore,":[240],"it":[241],"demonstrates":[242],"strong":[243],"scalability":[244],"respect":[246],"size":[250],"(2B":[251],"72B)":[253],"volume,":[257],"exhibits":[259],"promising":[260],"generalization":[261],"types":[264],"beyond":[265],"object-level":[266]},"counts_by_year":[],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2026-03-18T00:00:00"}