{"id":"https://openalex.org/W4415538710","doi":"https://doi.org/10.1145/3746027.3754993","title":"MIHBench: Benchmarking and Mitigating Multi-Image Hallucinations in Multimodal Large Language Models","display_name":"MIHBench: Benchmarking and Mitigating Multi-Image Hallucinations in Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538710","doi":"https://doi.org/10.1145/3746027.3754993"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3754993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.00726","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiale Li","orcid":"https://orcid.org/0009-0001-3717-1255"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Li","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0001-3717-1255","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099497155","display_name":"Mingrui Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingrui Wu","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China and Zhongguancun Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-8633-758X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China and Zhongguancun Academy, Beijing, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zixiang Jin","orcid":"https://orcid.org/0009-0008-8610-8739"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixiang Jin","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0008-8610-8739","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Chen","orcid":"https://orcid.org/0009-0008-4163-9392"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0008-4163-9392","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084510895","display_name":"Jiayi Ji","orcid":"https://orcid.org/0000-0002-9956-6308"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Ji","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0002-9956-6308","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059926864","display_name":"Xiaoshuai Sun","orcid":"https://orcid.org/0000-0003-3912-9306"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Sun","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0003-3912-9306","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014628588","display_name":"Liujuan Cao","orcid":"https://orcid.org/0000-0002-7645-9606"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liujuan Cao","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0002-7645-9606","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0001-9163-2932","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":1.4098,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84851301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3143","last_page":"3152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9907000064849854,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9907000064849854,"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/T10028","display_name":"Topic Modeling","score":0.9732999801635742,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9577999711036682,"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/visual-hallucination","display_name":"Visual Hallucination","score":0.6550999879837036},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6280999779701233},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5950000286102295},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5741000175476074},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5702999830245972},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5184999704360962},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.454800009727478},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.42910000681877136}],"concepts":[{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.6550999879837036},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6280999779701233},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5950000286102295},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5741000175476074},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5702999830245972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5604000091552734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5246000289916992},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5184999704360962},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.44600000977516174},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.42660000920295715},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3736000061035156},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30730000138282776},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29580000042915344},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2816999852657318},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2671000063419342}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3754993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.00726","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.00726","pdf_url":"https://arxiv.org/pdf/2508.00726","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.00726","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.00726","pdf_url":"https://arxiv.org/pdf/2508.00726","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6758050935","display_name":null,"funder_award_id":"No.2023M732948","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2963530300","https://openalex.org/W3167939936","https://openalex.org/W3196466825","https://openalex.org/W4312344082","https://openalex.org/W4389104841","https://openalex.org/W4402670231","https://openalex.org/W4402726948","https://openalex.org/W4402727536","https://openalex.org/W4402727851","https://openalex.org/W4404199641","https://openalex.org/W4405596328","https://openalex.org/W4408065099","https://openalex.org/W4413145939"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"growing":[1],"interest":[2],"in":[3,5,19,36,123,194],"hallucination":[4,18,111,118,185],"Multimodal":[6],"Large":[7],"Language":[8],"Models,":[9],"existing":[10],"studies":[11],"primarily":[12],"focus":[13],"on":[14,143],"single-image":[15,117],"settings,":[16],"leaving":[17],"multi-image":[20,37,95,124,195],"scenarios":[21],"largely":[22],"unexplored.":[23],"To":[24,151],"address":[25,152],"this":[26],"gap,":[27],"we":[28,86,155],"conduct":[29],"the":[30,92,102,108,127,134,144,169],"first":[31],"systematic":[32],"study":[33],"of":[34,94,104,110,129,137,146],"hallucinations":[35,49],"MLLMs":[38,178],"and":[39,66,79,107,120,126,133,187,191],"propose":[40,156],"MIHBench,":[41],"a":[42,98,113,157],"benchmark":[43],"specifically":[44],"tailored":[45],"for":[46],"evaluating":[47],"object-related":[48],"across":[50,74,175],"multiple":[51,176],"images.":[52],"MIHBench":[53],"comprises":[54],"three":[55],"core":[56],"tasks:":[57],"Multi-Image":[58,62],"Object":[59,63,67],"Existence":[60],"Hallucination,":[61,65,70],"Count":[64],"Identity":[68],"Consistency":[69],"targeting":[71],"semantic":[72,189],"understanding":[73],"object":[75,147],"existence,":[76],"quantity":[77],"reasoning,":[78],"cross-view":[80],"identity":[81,148],"consistency.":[82],"Through":[83],"extensive":[84],"evaluation,":[85],"identify":[87],"key":[88],"factors":[89],"associated":[90],"with":[91],"occurrence":[93,145],"hallucinations,":[96],"including:":[97],"progressive":[99],"relationship":[100],"between":[101,116],"number":[103],"image":[105,131,141],"inputs":[106],"likelihood":[109],"occurrences;":[112],"strong":[114],"correlation":[115],"tendencies":[119],"those":[121],"observed":[122],"contexts;":[125],"influence":[128],"same-object":[130],"ratios":[132],"positional":[135],"placement":[136],"negative":[138],"samples":[139],"within":[140],"sequences":[142],"consistency":[149],"hallucination.":[150],"these":[153],"challenges,":[154],"Dynamic":[158],"Attention":[159],"Balancing":[160],"mechanism":[161],"that":[162,180],"adjusts":[163],"inter-image":[164],"attention":[165,172],"distributions":[166],"while":[167],"preserving":[168],"overall":[170],"visual":[171],"proportion.":[173],"Experiments":[174],"state-of-the-art":[177],"demonstrate":[179],"our":[181],"method":[182],"effectively":[183],"reduces":[184],"occurrences":[186],"enhances":[188],"integration":[190],"reasoning":[192],"stability":[193],"scenarios.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-25T00:00:00"}
