{"id":"https://openalex.org/W4415541148","doi":"https://doi.org/10.1145/3746027.3755271","title":"MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models","display_name":"MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415541148","doi":"https://doi.org/10.1145/3746027.3755271"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755271","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755271","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":["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/A5109779844","display_name":"Qiyan Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyan Zhao","raw_affiliation_strings":["FKLPRIU, Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0001-5054-9742","affiliations":[{"raw_affiliation_string":"FKLPRIU, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455665","display_name":"Xiaofeng Zhang","orcid":"https://orcid.org/0000-0002-7185-4682"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Zhang","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7185-4682","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yiheng Li","orcid":"https://orcid.org/0009-0003-9154-0458"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yiheng Li","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0003-9154-0458","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779639","display_name":"Yun Xing","orcid":"https://orcid.org/0000-0001-9839-0120"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yun Xing","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9839-0120","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003035289","display_name":"Xiaosong Yuan","orcid":"https://orcid.org/0000-0001-5748-5174"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaosong Yuan","raw_affiliation_strings":["Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0001-5748-5174","affiliations":[{"raw_affiliation_string":"Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111230252","display_name":"Feilong Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Feilong Tang","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0009-0002-7583-482X","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030567406","display_name":"Sinan Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sinan Fan","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-5186-8834","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036370695","display_name":"Xuhang Chen","orcid":"https://orcid.org/0000-0001-6000-3914"},"institutions":[{"id":"https://openalex.org/I93477617","display_name":"Huizhou University","ror":"https://ror.org/03q3s7962","country_code":"CN","type":"education","lineage":["https://openalex.org/I93477617"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuhang Chen","raw_affiliation_strings":["Huizhou University, Huizhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6000-3914","affiliations":[{"raw_affiliation_string":"Huizhou University, Huizhou, China","institution_ids":["https://openalex.org/I93477617"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032628425","display_name":"Da\u2010Han Wang","orcid":"https://orcid.org/0000-0002-5901-0778"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da-Han Wang","raw_affiliation_strings":["FKLPRIU, Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-5901-0778","affiliations":[{"raw_affiliation_string":"FKLPRIU, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082548671","display_name":"Xu-Yao Zhang","orcid":"https://orcid.org/0000-0001-9260-188X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu-Yao Zhang","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9260-188X","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"3981","last_page":"3990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9975000023841858,"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":0.9975000023841858,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9872000217437744,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9782000184059143,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6969000101089478},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5767999887466431},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5590999722480774},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.48840001225471497},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4708000123500824},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43810001015663147},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4228000044822693},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4056999981403351}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6969000101089478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6290000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.60589998960495},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5767999887466431},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5590999722480774},{"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/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43810001015663147},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4056999981403351},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.34709998965263367},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.32760000228881836},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.28850001096725464},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27880001068115234},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C184047640","wikidata":"https://www.wikidata.org/wiki/Q182593","display_name":"Illusion","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C3018151503","wikidata":"https://www.wikidata.org/wiki/Q608487","display_name":"Hand position","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755271","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755271","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2963622213","https://openalex.org/W3016211260","https://openalex.org/W4402727851","https://openalex.org/W4403791273","https://openalex.org/W4403939369","https://openalex.org/W4413144618"],"related_works":[],"abstract_inverted_index":{"Hallucinations":[0],"pose":[1],"a":[2,18,132],"significant":[3],"challenge":[4],"in":[5,32,41,74,180],"Large":[6],"Vision":[7],"Language":[8],"Models":[9],"(LVLMs),":[10],"with":[11],"misalignment":[12],"between":[13],"multimodal":[14,44,97],"features":[15],"identified":[16],"as":[17,104],"key":[19],"contributing":[20],"factor.":[21],"This":[22,87],"paper":[23],"reveals":[24],"the":[25,29,63,70,75,84,128,139],"negative":[26],"impact":[27],"of":[28,55,112,147,162],"long-term":[30,48,129],"decay":[31,130],"Rotary":[33],"Position":[34],"Encoding":[35],"(RoPE),":[36],"used":[37],"for":[38,150],"positional":[39,151],"modeling":[40],"LVLMs,":[42],"on":[43,123],"alignment.":[45,98],"Concretely,":[46],"under":[47],"decay,":[49],"instruction":[50,85],"tokens":[51,57,68,79,114,149],"exhibit":[52],"uneven":[53],"perception":[54,89,111],"image":[56,67,113,148,157],"located":[58],"at":[59,115],"different":[60,116],"positions":[61],"within":[62],"two-dimensional":[64,144],"space:":[65],"prioritizing":[66],"from":[69],"bottom-right":[71],"region":[72],"since":[73],"one-dimensional":[76,140],"sequence,":[77],"these":[78],"are":[80],"positionally":[81],"closer":[82],"to":[83,91,101,131],"tokens.":[86],"biased":[88],"leads":[90],"insufficient":[92],"image-instruction":[93],"interaction":[94],"and":[95,143,167,173],"suboptimal":[96],"We":[99],"refer":[100],"this":[102],"phenomenon":[103],"''image":[105],"alignment":[106,158],"bias.''":[107],"To":[108],"enhance":[109],"instruction's":[110],"spatial":[117,135,145],"locations,":[118],"we":[119],"propose":[120],"MCA-LLaVA,":[121],"based":[122],"Manhattan":[124],"distance,":[125],"which":[126],"extends":[127],"two-dimensional,":[133],"multi-directional":[134],"decay.":[136],"MCA-LLaVA":[137,163],"integrates":[138],"sequence":[141],"order":[142],"position":[146],"modeling,":[152],"mitigating":[153],"hallucinations":[154],"by":[155],"alleviating":[156],"bias.":[159],"Experimental":[160],"results":[161],"across":[164],"various":[165],"hallucination":[166],"general":[168],"benchmarks":[169],"demonstrate":[170],"its":[171],"effectiveness":[172],"generality.":[174],"The":[175],"code":[176],"can":[177],"be":[178],"accessed":[179],"https://github.com/ErikZ719/MCA-LLaVA.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
