{"id":"https://openalex.org/W4414360033","doi":"https://doi.org/10.24963/ijcai.2025/212","title":"Understanding Visual Detail Hallucinations of Large Vision-Language Models","display_name":"Understanding Visual Detail Hallucinations of Large Vision-Language Models","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360033","doi":"https://doi.org/10.24963/ijcai.2025/212"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/212","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-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":"https://openalex.org/A5109233343","display_name":"Xiaoxi Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoxi Sun","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060384601","display_name":"Jianxin Liang","orcid":"https://orcid.org/0000-0002-6636-0872"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxin Liang","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102564905","display_name":"Yueqian Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueqian Wang","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042848593","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0002-6669-0839"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huishuai Zhang","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037132097","display_name":"Dongyan Zhao","orcid":"https://orcid.org/0000-0002-0396-6703"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongyan Zhao","raw_affiliation_strings":["Peking University","State Key Laboratory of General Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109233343"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26672274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1900","last_page":"1908"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13397","display_name":"Hallucinations in medical conditions","score":0.8912000060081482,"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"}},"topics":[{"id":"https://openalex.org/T13397","display_name":"Hallucinations in medical conditions","score":0.8912000060081482,"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/T10241","display_name":"Functional Brain Connectivity Studies","score":0.8187999725341797,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.7972000241279602,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6132000088691711},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.5302000045776367},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5015000104904175},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4950000047683716},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4799000024795532},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.3765999972820282},{"id":"https://openalex.org/keywords/visual-objects","display_name":"Visual Objects","score":0.3564000129699707},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3483000099658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7182000279426575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6625999808311462},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6132000088691711},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.5302000045776367},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5092999935150146},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4950000047683716},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3765999972820282},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.3564000129699707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C105842133","wikidata":"https://www.wikidata.org/wiki/Q1899679","display_name":"Visual communication","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2903999984264374},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2858999967575073},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26350000500679016}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/212","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"small":[1,34,81,101,206],"visual":[2,37,50,113,149,158,186],"objects":[3,35,82,91],"is":[4,167,188],"crucial":[5],"in":[6,36,133],"fields":[7],"such":[8],"as":[9,71],"video":[10],"surveillance,":[11],"remote":[12],"sensing,":[13],"and":[14,32,56,126],"autonomous":[15],"driving.":[16],"In":[17,174],"this":[18,40],"paper,":[19],"we":[20,42,62,116,139],"investigate":[21],"the":[22,106,148],"capability":[23],"of":[24,59,98,123,130,136,143,151,180],"advanced":[25],"large":[26],"vision-language":[27],"models":[28],"(LVLMs)":[29],"to":[30,80,84,93],"recognize":[31],"interpret":[33],"data.":[38],"To":[39],"end,":[41],"curate":[43],"a":[44,141,195],"specialized":[45],"dataset":[46],"for":[47,108,169,176,204],"evaluating":[48],"fine-grained":[49,112,157],"hallucinations,":[51,181],"incorporating":[52],"two":[53],"object":[54,170,207],"categories":[55],"three":[57,118],"types":[58,179],"hallucinations.":[60,114],"First,":[61],"assess":[63],"11":[64],"state-of-the-art":[65],"LVLMs,":[66],"yielding":[67],"several":[68,201],"key":[69],"insights,":[70],"anticipated,":[72],"LVLMs":[73],"perform":[74],"significantly":[75,189],"worse":[76],"on":[77,89,100,111,147,194],"queries":[78],"related":[79],"compared":[83],"regular-sized":[85],"ones,":[86],"with":[87,209],"performance":[88,155],"regular":[90],"proving":[92],"be":[94],"an":[95],"unreliable":[96],"predictor":[97],"that":[99,164],"objects.":[102],"This":[103],"finding":[104],"underscores":[105],"need":[107],"dedicated":[109],"research":[110],"Second,":[115],"evaluate":[117],"training-free":[119],"methods:":[120],"Scaffold,":[121],"Chain":[122],"Thought":[124],"(CoT),":[125],"Image":[127],"Resizing,":[128],"all":[129],"which":[131],"result":[132],"varying":[134],"degrees":[135],"improvement.":[137],"Furthermore,":[138],"conduct":[140],"series":[142],"detailed":[144],"ablation":[145],"studies":[146],"encoders":[150,187],"Eagle-X5,":[152],"examining":[153],"their":[154],"across":[156],"hallucination":[159],"tasks.":[160,173],"Our":[161],"findings":[162],"reveal":[163],"ConvNeXt":[165],"architecture":[166],"critical":[168],"existence":[171],"recognition":[172,208],"contrast,":[175],"mitigating":[177],"other":[178],"integrating":[182],"information":[183],"from":[184],"multiple":[185],"more":[190],"effective":[191],"than":[192],"relying":[193],"single":[196],"encoder.":[197],"These":[198],"results":[199],"highlight":[200],"promising":[202],"directions":[203],"advancing":[205],"LVLMs.":[210]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}