{"id":"https://openalex.org/W4415709510","doi":"https://doi.org/10.1109/icme59968.2025.11209139","title":"Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models","display_name":"Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709510","doi":"https://doi.org/10.1109/icme59968.2025.11209139"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100744772","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-4028-0938"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["Northwestern Polytechnical University,School of Automation,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Automation,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062149619","display_name":"Dehong Gao","orcid":"https://orcid.org/0000-0002-6636-5702"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dehong Gao","raw_affiliation_strings":["Northwestern Polytechnical University,School of Cybersecurity,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Cybersecurity,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103885616","display_name":"Y. Wang","orcid":"https://orcid.org/0000-0002-3210-2330"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yeyuan Wang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Automation,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Automation,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075971838","display_name":"Linbo Jin","orcid":"https://orcid.org/0000-0003-3201-2113"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linbo Jin","raw_affiliation_strings":["Alibaba Group,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063370205","display_name":"Shanqing Yu","orcid":"https://orcid.org/0000-0001-5170-8082"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanqing Yu","raw_affiliation_strings":["Zhejiang University of Technology,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070472433","display_name":"Xiaoyan Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Cai","raw_affiliation_strings":["Northwestern Polytechnical University,School of Automation,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Automation,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101972632","display_name":"Libin Yang","orcid":"https://orcid.org/0000-0002-7203-0810"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libin Yang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Cybersecurity,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Cybersecurity,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.517799973487854,"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":0.517799973487854,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.02979999966919422,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.026399999856948853,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5447999835014343},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5005000233650208},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4625999927520752},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.4146000146865845},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.36800000071525574},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3231000006198883},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3224000036716461},{"id":"https://openalex.org/keywords/selective-attention","display_name":"Selective attention","score":0.3046000003814697},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.304500013589859}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692300021648407},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.541700005531311},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5005000233650208},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4625999927520752},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.4146000146865845},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.39590001106262207},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32510000467300415},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3203999996185303},{"id":"https://openalex.org/C2989146674","wikidata":"https://www.wikidata.org/wiki/Q4818236","display_name":"Selective attention","level":3,"score":0.3046000003814697},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.303600013256073},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2994000017642975},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29350000619888306},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27880001068115234},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2766000032424927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2964138343","https://openalex.org/W3035485997","https://openalex.org/W3165938948","https://openalex.org/W3198377975","https://openalex.org/W3212386989","https://openalex.org/W4220798687","https://openalex.org/W4322207844","https://openalex.org/W4390873481","https://openalex.org/W4396843958","https://openalex.org/W4402670231","https://openalex.org/W4402726945","https://openalex.org/W4402753774","https://openalex.org/W4404534210","https://openalex.org/W4404612908","https://openalex.org/W4404682098","https://openalex.org/W4404782664","https://openalex.org/W4404783238","https://openalex.org/W4405596328","https://openalex.org/W4408354084","https://openalex.org/W4409366315","https://openalex.org/W4412888840"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,44,48,81,93],"significant":[2],"success":[3],"of":[4],"Large":[5],"Vision-Language":[6],"models(LVLMs),":[7],"these":[8,26],"models":[9,27],"still":[10],"suffer":[11],"hallucinations":[12],"when":[13],"describing":[14],"images,":[15],"generating":[16],"answers":[17],"that":[18,25,36,103],"include":[19],"non-factual":[20],"objects.":[21],"It":[22],"is":[23,125],"reported":[24],"tend":[28],"to":[29,96],"overfocus":[30],"on":[31,110],"certain":[32],"irrelevant":[33,62,89,97],"image":[34,86,90],"tokens":[35,63,87],"do":[37],"not":[38],"contain":[39],"critical":[40],"information":[41],"for":[42],"answering":[43],"question":[45],"and":[46,88,116],"distort":[47],"output.":[49],"To":[50],"address":[51],"this,":[52],"we":[53,78],"propose":[54],"an":[55],"Instruction-Aligned":[56],"Visual":[57],"Attention(IAVA)":[58],"approach,":[59],"which":[60],"identifies":[61],"by":[64],"comparing":[65],"changes":[66],"in":[67,118],"attention":[68],"weights":[69],"under":[70],"two":[71],"different":[72],"instructions.":[73],"By":[74],"applying":[75],"contrastive":[76],"decoding,":[77],"dynamically":[79],"adjust":[80],"logits":[82],"generated":[83],"from":[84],"original":[85],"tokens,":[91],"reducing":[92],"model\u2019s":[94],"over-attention":[95],"information.":[98],"The":[99],"experimental":[100],"results":[101],"demonstrate":[102],"IAVA":[104,123],"consistently":[105],"outperforms":[106],"existing":[107],"decoding":[108],"techniques":[109],"benchmarks":[111],"such":[112],"as":[113],"MME,":[114],"POPE,":[115],"TextVQA":[117],"mitigating":[119],"object":[120],"hallucinations.":[121],"Our":[122],"approach":[124],"available":[126],"online":[127],"at":[128],"https://github.com/Lee-lab558/IAVA.":[129]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}
