{"id":"https://openalex.org/W4415538379","doi":"https://doi.org/10.1145/3746027.3762061","title":"DeepSIX at ACM MM 2025 Grand Challenge: Enhancing Context Text Processing for Multimodal Hallucination Detection and Fact Verification","display_name":"DeepSIX at ACM MM 2025 Grand Challenge: Enhancing Context Text Processing for Multimodal Hallucination Detection and Fact Verification","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538379","doi":"https://doi.org/10.1145/3746027.3762061"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3762061","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762061","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":"article","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":null,"display_name":"Hoang Chu","orcid":"https://orcid.org/0009-0005-4549-8417"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hoang Chu","raw_affiliation_strings":["Japan Institute of Science and Technology, Nomi, Ishikawa, Japan"],"raw_orcid":"https://orcid.org/0009-0005-4549-8417","affiliations":[{"raw_affiliation_string":"Japan Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huy Chu","orcid":"https://orcid.org/0009-0000-3413-0688"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Huy Chu","raw_affiliation_strings":["Japan Institute of Science and Technology, Nomi, Ishikawa, Japan"],"raw_orcid":"https://orcid.org/0009-0000-3413-0688","affiliations":[{"raw_affiliation_string":"Japan Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061935797","display_name":"Tan-Minh Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tan-Minh Nguyen","raw_affiliation_strings":["Japan Institute of Science and Technology, Nomi, Ishikawa, Japan"],"raw_orcid":"https://orcid.org/0009-0001-3139-6349","affiliations":[{"raw_affiliation_string":"Japan Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069724988","display_name":"Son T. Luu","orcid":"https://orcid.org/0000-0002-1231-5865"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Son T. Luu","raw_affiliation_strings":["Japan Institute of Science and Technology, Nomi, Ishikawa, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1231-5865","affiliations":[{"raw_affiliation_string":"Japan Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109139032","display_name":"Cuong Hoang","orcid":"https://orcid.org/0009-0005-2583-5332"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Cuong Hoang","raw_affiliation_strings":["Japan Institute of Science and Technology, Nomi, Ishikawa, Japan"],"raw_orcid":"https://orcid.org/0009-0005-2583-5332","affiliations":[{"raw_affiliation_string":"Japan Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hiep Nguyen","orcid":"https://orcid.org/0009-0003-0826-0827"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiep Nguyen","raw_affiliation_strings":["Japan Institute of Science and Technology, Nomi, Ishikawa, Japan"],"raw_orcid":"https://orcid.org/0009-0003-0826-0827","affiliations":[{"raw_affiliation_string":"Japan Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018668377","display_name":"Vu Tran","orcid":"https://orcid.org/0000-0002-0249-7570"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Vu Tran","raw_affiliation_strings":["Japan Institute of Science and Technology, Nomi, Ishikawa, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0249-7570","affiliations":[{"raw_affiliation_string":"Japan Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077641909","display_name":"Le-Minh Nguyen","orcid":"https://orcid.org/0000-0002-2265-1010"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Le-Minh Nguyen","raw_affiliation_strings":["Nguyen Lab, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2265-1010","affiliations":[{"raw_affiliation_string":"Nguyen Lab, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0646,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92864346,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"13874","last_page":"13880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.9711999893188477,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12268","display_name":"Deception detection and forensic psychology","score":0.9684000015258789,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5961999893188477},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.5138999819755554},{"id":"https://openalex.org/keywords/anaphora","display_name":"Anaphora (linguistics)","score":0.5088000297546387},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4853000044822693},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3849000036716461},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.3483000099658966},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.33090001344680786},{"id":"https://openalex.org/keywords/grammaticality","display_name":"Grammaticality","score":0.3285999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569000124931335},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6025000214576721},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5536999702453613},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C2781449363","wikidata":"https://www.wikidata.org/wiki/Q156751","display_name":"Anaphora (linguistics)","level":3,"score":0.5088000297546387},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.33090001344680786},{"id":"https://openalex.org/C2779525943","wikidata":"https://www.wikidata.org/wiki/Q1187300","display_name":"Grammaticality","level":3,"score":0.3285999894142151},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2757999897003174},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C11693617","wikidata":"https://www.wikidata.org/wiki/Q181839","display_name":"Pragmatics","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3762061","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762061","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2516338333","https://openalex.org/W2743800013","https://openalex.org/W2759820691","https://openalex.org/W3157152818","https://openalex.org/W4282925409","https://openalex.org/W4287603409","https://openalex.org/W4389523832","https://openalex.org/W4402670859","https://openalex.org/W4403507530","https://openalex.org/W4411119874"],"related_works":[],"abstract_inverted_index":{"Significant":[0],"advancements":[1],"have":[2],"been":[3],"achieved":[4,216],"in":[5,38,59,73,90,122,172,177,190,219,227,238],"both":[6,123],"fields":[7],"of":[8,20,106,142,148,212,235],"Natural":[9],"Language":[10,23],"Processing":[11],"(NLP)":[12],"and":[13,69,99,115,130,145,155,160,175,199,201,204,224],"Computer":[14],"Vision":[15],"(CV)":[16],"with":[17,56],"the":[18,57,94,104,107,139,143,173,178,191,210,220,228,233],"advent":[19],"Multimodal":[21,117,125,131],"Large":[22],"Models":[24],"(MLLMs),":[25],"sometimes":[26],"referred":[27],"to":[28,66,92,96,153],"as":[29,42],"large":[30],"vision-language":[31],"models":[32,62,151],"(LVMs).":[33],"MLLMs":[34,91],"show":[35],"promising":[36],"ability":[37,95],"multimodal":[39],"tasks,":[40],"such":[41],"image":[43],"captioning,":[44],"visual":[45],"question":[46],"answering,":[47],"etc.":[48],"However,":[49],"there":[50],"is":[51],"a":[52],"concerning":[53],"trend":[54],"associated":[55],"advancement":[58],"MLLMs.":[60,239],"These":[61],"exhibit":[63],"an":[64],"inclination":[65],"generate":[67],"hallucinations":[68,203],"misleading":[70],"facts,":[71],"resulting":[72],"seemingly":[74],"plausible":[75],"yet":[76],"factually":[77],"spurious":[78],"content.":[79],"To":[80],"address":[81],"these":[82],"challenges,":[83],"our":[84,185,213,242],"team,":[85],"DeepSIX,":[86],"leverages":[87,138],"recent":[88],"advances":[89],"enhance":[93],"detect":[97],"hallucination":[98],"verify":[100],"factual":[101],"information":[102],"within":[103],"scope":[105],"ACM":[108],"MM":[109],"2025":[110],"grand":[111],"challenge":[112],"8:":[113],"Truthful":[114],"Responsible":[116],"Learning":[118],"(ResMM).":[119],"We":[120,240],"participated":[121],"tasks:":[124],"Hallucination":[126,221],"Detection":[127,222],"(Task":[128,134],"1)":[129],"Fact":[132,229],"Checking":[133],"2).":[135],"Our":[136],"approach":[137],"interpretive":[140],"power":[141],"vision":[144,149],"language":[146,150],"components":[147],"(VLMs)":[152],"analyze":[154],"summarize":[156],"insights":[157],"from":[158],"text":[159,174,198],"images.":[161,179],"It":[162],"performs":[163],"contextual":[164],"reasoning":[165],"by":[166],"uncovering":[167],"semantic":[168],"relationships":[169,196],"among":[170],"entities":[171,189],"objects":[176],"By":[180],"employing":[181],"diverse":[182],"prompting":[183],"techniques,":[184],"method":[186],"deconstructs":[187],"critical":[188],"text,":[192],"effectively":[193],"uncovers":[194],"implicit":[195],"between":[197],"images,":[200],"identifies":[202],"false":[205],"facts.":[206],"Experimental":[207],"results":[208],"demonstrate":[209],"strength":[211],"approach:":[214],"it":[215],"second":[217],"place":[218,226],"task":[223],"third":[225],"Verification":[230],"task,":[231],"confirming":[232],"potential":[234],"LLM-based":[236],"methods":[237],"open-source":[241],"code":[243],"at":[244],"https://github.com/JAIST-DeepSIX/ACMMM25":[245]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}