{"id":"https://openalex.org/W4415536782","doi":"https://doi.org/10.1145/3746027.3755044","title":"See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs","display_name":"See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536782","doi":"https://doi.org/10.1145/3746027.3755044"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755044","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755044","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/2507.22003","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ziyun Dai","orcid":"https://orcid.org/0009-0002-4403-896X"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyun Dai","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-4403-896X","affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339621","display_name":"Xiaoqiang Li","orcid":"https://orcid.org/0000-0001-7243-2783"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqiang Li","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7243-2783","affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107746826","display_name":"Shaohua Zhang","orcid":"https://orcid.org/0000-0001-9289-3827"},"institutions":[{"id":"https://openalex.org/I153806059","display_name":"Shanghai Business School","ror":"https://ror.org/05kf5z787","country_code":"CN","type":"education","lineage":["https://openalex.org/I153806059"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohua Zhang","raw_affiliation_strings":["Shanghai Business School, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9289-3827","affiliations":[{"raw_affiliation_string":"Shanghai Business School, Shanghai, China","institution_ids":["https://openalex.org/I153806059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084918752","display_name":"Yuanchen Wu","orcid":"https://orcid.org/0000-0003-4079-4725"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanchen Wu","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4079-4725","affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046247173","display_name":"Jide Li","orcid":"https://orcid.org/0000-0002-0754-5842"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jide Li","raw_affiliation_strings":["Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0754-5842","affiliations":[{"raw_affiliation_string":"Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2841248,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3310","last_page":"3319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13397","display_name":"Hallucinations in medical conditions","score":0.9387999773025513,"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":0.9387999773025513,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-hallucination","display_name":"Visual Hallucination","score":0.8263999819755554},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.48539999127388},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4738999903202057},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.46309998631477356},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.38109999895095825},{"id":"https://openalex.org/keywords/n2pc","display_name":"N2pc","score":0.31189998984336853},{"id":"https://openalex.org/keywords/visual-inspection","display_name":"Visual inspection","score":0.30790001153945923}],"concepts":[{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.8263999819755554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.536899983882904},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4837000072002411},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.46309998631477356},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4074000120162964},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.39469999074935913},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.38109999895095825},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36959999799728394},{"id":"https://openalex.org/C207357515","wikidata":"https://www.wikidata.org/wiki/Q6951948","display_name":"N2pc","level":4,"score":0.31189998984336853},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C63075964","wikidata":"https://www.wikidata.org/wiki/Q3277307","display_name":"Visual rhetoric","level":3,"score":0.25360000133514404},{"id":"https://openalex.org/C2778251979","wikidata":"https://www.wikidata.org/wiki/Q7936617","display_name":"Visual processing","level":3,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755044","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755044","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:2507.22003","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.22003","pdf_url":"https://arxiv.org/pdf/2507.22003","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:2507.22003","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.22003","pdf_url":"https://arxiv.org/pdf/2507.22003","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W3106743555","https://openalex.org/W4390873054","https://openalex.org/W4393148714","https://openalex.org/W4394625786","https://openalex.org/W4402727764"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"capabilities":[7],"in":[8],"visual":[9,32,55,85,90,104,112,125,145,157],"understanding":[10,56,146],"and":[11,79,127,165],"multimodal":[12],"reasoning.":[13],"However,":[14],"LVLMs":[15,107],"frequently":[16],"exhibit":[17],"hallucination":[18,35,150,163],"phenomena,":[19],"manifesting":[20],"as":[21],"the":[22,30,41,94,122],"generated":[23],"textual":[24],"responses":[25],"that":[26,70,139],"demonstrate":[27],"inconsistencies":[28],"with":[29,53,88,101],"provided":[31],"content.":[33],"Existing":[34],"mitigation":[36,68,164],"methods":[37],"are":[38],"predominantly":[39],"text-centric,":[40],"challenges":[42],"of":[43],"visual-semantic":[44,72,131,166],"alignment":[45,73],"significantly":[46,148],"limit":[47],"their":[48],"effectiveness,":[49],"especially":[50],"when":[51],"confronted":[52],"fine-grained":[54,111,144],"scenarios.":[57],"To":[58],"this":[59,61],"end,":[60],"paper":[62],"presents":[63],"ViHallu,":[64],"a":[65,156],"Vision-Centric":[66],"Hallucination":[67],"framework":[69],"enhances":[71,142],"through":[74,114],"Visual":[75,80],"Variation":[76],"Image":[77],"Generation":[78],"Instruction":[81],"Construction.":[82],"ViHallu":[83,140],"introduces":[84],"variation":[86],"images":[87],"controllable":[89],"alterations":[91],"while":[92,147],"maintaining":[93],"overall":[95],"image":[96],"structure.":[97],"These":[98],"images,":[99],"combined":[100],"carefully":[102],"constructed":[103],"instructions,":[105],"enable":[106],"to":[108,118],"better":[109],"understand":[110],"content":[113,126],"fine-tuning,":[115],"allowing":[116],"models":[117],"more":[119],"precisely":[120],"capture":[121],"correspondence":[123],"between":[124],"text,":[128],"thereby":[129],"enhancing":[130],"alignment.":[132,167],"Extensive":[133],"experiments":[134],"on":[135],"multiple":[136],"benchmarks":[137],"show":[138],"effectively":[141],"models'":[143],"reducing":[149],"tendencies.":[151],"Furthermore,":[152],"we":[153],"release":[154],"ViHallu-Instruction,":[155],"instruction":[158],"dataset":[159],"specifically":[160],"designed":[161],"for":[162],"Code":[168],"is":[169],"available":[170],"at":[171],"https://github.com/oliviadzy/ViHallu.":[172]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-25T00:00:00"}
