{"id":"https://openalex.org/W4415538052","doi":"https://doi.org/10.1145/3746027.3762014","title":"HKD4VLM: A Progressive Hybrid Knowledge Distillation Framework for Robust Multimodal Hallucination and Factuality Detection in VLMs","display_name":"HKD4VLM: A Progressive Hybrid Knowledge Distillation Framework for Robust Multimodal Hallucination and Factuality Detection in VLMs","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538052","doi":"https://doi.org/10.1145/3746027.3762014"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3762014","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762014","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/A5101864810","display_name":"Zijian Zhang","orcid":"https://orcid.org/0000-0002-1748-4924"},"institutions":[{"id":"https://openalex.org/I4210101987","display_name":"MEI Research (United States)","ror":"https://ror.org/01797xg87","country_code":"US","type":"company","lineage":["https://openalex.org/I4210101987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zijian Zhang","raw_affiliation_strings":["Meituan-M17, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1748-4924","affiliations":[{"raw_affiliation_string":"Meituan-M17, Shanghai, China","institution_ids":["https://openalex.org/I4210101987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108497986","display_name":"Xuecheng Wu","orcid":"https://orcid.org/0000-0002-6244-0269"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuecheng Wu","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-6244-0269","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043360673","display_name":"Danlei Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danlei Huang","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0008-5929-6455","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siyu Yan","orcid":"https://orcid.org/0009-0006-4701-3054"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Yan","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-4701-3054","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083536273","display_name":"Chong Peng","orcid":"https://orcid.org/0000-0002-6070-3600"},"institutions":[{"id":"https://openalex.org/I4210101987","display_name":"MEI Research (United States)","ror":"https://ror.org/01797xg87","country_code":"US","type":"company","lineage":["https://openalex.org/I4210101987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chong Peng","raw_affiliation_strings":["Meituan-M17, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6070-3600","affiliations":[{"raw_affiliation_string":"Meituan-M17, Shanghai, China","institution_ids":["https://openalex.org/I4210101987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108060642","display_name":"Xuezhi Cao","orcid":"https://orcid.org/0000-0002-7044-1341"},"institutions":[{"id":"https://openalex.org/I4210101987","display_name":"MEI Research (United States)","ror":"https://ror.org/01797xg87","country_code":"US","type":"company","lineage":["https://openalex.org/I4210101987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuezhi Cao","raw_affiliation_strings":["Meituan-M17, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7044-1341","affiliations":[{"raw_affiliation_string":"Meituan-M17, Shanghai, China","institution_ids":["https://openalex.org/I4210101987"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.346,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93347753,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"13881","last_page":"13887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9962999820709229,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9962999820709229,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9588000178337097,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9072999954223633,"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/inference","display_name":"Inference","score":0.6987000107765198},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6966999769210815},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6812999844551086},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5407000184059143},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4171999990940094},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.33959999680519104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261999845504761},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6987000107765198},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6966999769210815},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6812999844551086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6586999893188477},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.501800000667572},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3762014","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762014","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":5,"referenced_works":["https://openalex.org/W4391094120","https://openalex.org/W4391136507","https://openalex.org/W4402671413","https://openalex.org/W4403780501","https://openalex.org/W4403842129"],"related_works":[],"abstract_inverted_index":{"Driven":[0],"by":[1],"the":[2,9,35,38,47,67,81,97,125,143,153],"rapid":[3],"progress":[4],"in":[5],"vision-language":[6],"models":[7,15],"(VLMs),":[8],"responsible":[10],"behavior":[11],"of":[12,41,83,145],"large-scale":[13],"multimodal":[14],"has":[16],"become":[17],"a":[18,52,59,88],"prominent":[19],"research":[20],"area,":[21],"particularly":[22],"focusing":[23],"on":[24,66],"hallucination":[25],"detection":[26],"and":[27,86,108,129,137],"factuality":[28],"checking.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,122],"present":[34],"solution":[36],"for":[37],"two":[39,78],"tracks":[40],"Responsible":[42],"AI":[43],"challenge.":[44],"Inspirations":[45],"from":[46,80,114],"general":[48],"domain":[49],"demonstrate":[50,142],"that":[51,62],"smaller":[53],"distilled":[54],"VLM":[55,61],"can":[56,100],"often":[57],"outperform":[58],"larger":[60],"is":[63],"directly":[64],"tuned":[65],"downstream":[68],"tasks,":[69],"while":[70],"achieving":[71],"higher":[72],"efficiency.":[73],"We":[74],"thus":[75],"jointly":[76],"tackle":[77],"tasks":[79],"perspective":[82],"knowledge":[84,91,116],"distillation":[85,92],"propose":[87],"progressive":[89],"hybrid":[90],"framework":[93,99],"termed":[94],"HKD4VLM.":[95,147],"Specifically,":[96],"overall":[98],"be":[101],"decomposed":[102],"into":[103,152],"Pyramid-like":[104],"Progressive":[105],"Online":[106],"Distillation":[107],"Ternary-Coupled":[109],"Refinement":[110],"Distillation,":[111],"hierarchically":[112],"moving":[113],"coarse-grained":[115],"alignment":[117],"to":[118,133],"fine-grained":[119],"refinement.":[120],"Besides,":[121],"further":[123],"introduce":[124],"mapping":[126],"shift-enhanced":[127],"inference":[128],"diverse":[130],"augmentation":[131],"strategies":[132],"enhance":[134],"model":[135],"performance":[136,158],"robustness.":[138],"Extensive":[139],"experimental":[140],"results":[141],"effectiveness":[144],"our":[146],"Ablation":[148],"studies":[149],"provide":[150],"insights":[151],"critical":[154],"design":[155],"choices":[156],"driving":[157],"gains.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}