{"id":"https://openalex.org/W4403780645","doi":"https://doi.org/10.1145/3664647.3681467","title":"AIGCs Confuse AI Too: Investigating and Explaining Synthetic Image-induced Hallucinations in Large Vision-Language Models","display_name":"AIGCs Confuse AI Too: Investigating and Explaining Synthetic Image-induced Hallucinations in Large Vision-Language Models","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780645","doi":"https://doi.org/10.1145/3664647.3681467"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681467","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5015589594","display_name":"Yifei Gao","orcid":"https://orcid.org/0000-0003-4367-450X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Gao","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4367-450X","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaqi Wang","orcid":"https://orcid.org/0009-0001-2301-3934"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Wang","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-2301-3934","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014416676","display_name":"Zhiyu Lin","orcid":"https://orcid.org/0000-0002-1120-2447"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyu Lin","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1120-2447","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023834030","display_name":"Jitao Sang","orcid":"https://orcid.org/0000-0002-0699-3205"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jitao Sang","raw_affiliation_strings":["Beijing Jiaotong University & Peng Cheng Lab, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0699-3205","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University & Peng Cheng Lab, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9010","last_page":"9018"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9724000096321106,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9724000096321106,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"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":0.9610000252723694,"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"}},{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.9531000256538391,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.5849934816360474},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5776556730270386},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.514553964138031},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5024757385253906},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43486273288726807},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3982846140861511},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3973897099494934},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3584309220314026}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5849934816360474},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5776556730270386},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.514553964138031},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5024757385253906},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43486273288726807},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3982846140861511},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3973897099494934},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3584309220314026}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681467","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.49000000953674316,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W4212774754","https://openalex.org/W4312933868","https://openalex.org/W4367595583","https://openalex.org/W4386187689","https://openalex.org/W4394862623"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935","https://openalex.org/W2563206327","https://openalex.org/W2069885731"],"abstract_inverted_index":{"The":[0,13],"evolution":[1],"of":[2,39],"Artificial":[3],"Intelligence":[4],"Generated":[5],"Contents":[6],"(AIGCs)":[7],"is":[8],"advancing":[9],"towards":[10],"higher":[11],"quality.":[12],"growing":[14],"interactions":[15],"with":[16],"AIGCs":[17],"present":[18,149],"a":[19,32,36,95,110,114],"new":[20],"challenge":[21],"to":[22,67,133],"the":[23,42,76,100,157],"data-driven":[24],"AI":[25,40,63],"community:":[26],"While":[27],"AI-generated":[28,57],"contents":[29],"have":[30,48],"played":[31],"crucial":[33],"role":[34],"in":[35,80],"wide":[37],"range":[38],"models,":[41],"potential":[43,60],"hidden":[44],"risks":[45],"they":[46],"introduce":[47],"not":[49,124],"been":[50],"thoroughly":[51],"examined.":[52],"Beyond":[53],"human-oriented":[54],"forgery":[55],"detection,":[56],"content":[58],"poses":[59],"issues":[61],"for":[62],"models":[64],"originally":[65],"designed":[66],"process":[68],"natural":[69,134],"data.":[70],"In":[71],"this":[72],"study,":[73],"we":[74],"underscore":[75],"exacerbated":[77],"hallucination":[78,98,158],"phenomena":[79],"Large":[81],"Vision-Language":[82],"Models":[83],"(LVLMs)":[84],"caused":[85],"by":[86,104,109],"AI-synthetic":[87],"images.":[88,135],"Remarkably,":[89],"our":[90,137],"findings":[91],"shed":[92],"light":[93],"on":[94,139],"consistent":[96],"AIGC":[97],"bias:":[99],"object":[101],"hallucinations":[102],"induced":[103],"synthetic":[105,121,146],"images":[106,122,147],"are":[107],"characterized":[108],"greater":[111],"quantity":[112],"and":[113,141],"more":[115],"uniform":[116],"position":[117],"distribution,":[118],"even":[119],"these":[120],"do":[123],"manifest":[125],"unrealistic":[126],"or":[127],"additional":[128],"relevant":[129],"visual":[130,153],"features":[131],"compared":[132],"Moreover,":[136],"investigations":[138],"Q-former":[140],"Linear":[142],"projector":[143],"reveal":[144],"that":[145],"may":[148],"token":[150],"deviations":[151],"after":[152],"projection,":[154],"thereby":[155],"amplifying":[156],"bias.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}