{"id":"https://openalex.org/W4414197458","doi":"https://doi.org/10.26599/bdma.2025.9020032","title":"Zero-Shot Knowledge-Based Visual Question Answering with Frozen Language Models","display_name":"Zero-Shot Knowledge-Based Visual Question Answering with Frozen Language Models","publication_year":2025,"publication_date":"2025-09-15","ids":{"openalex":"https://openalex.org/W4414197458","doi":"https://doi.org/10.26599/bdma.2025.9020032"},"language":"en","primary_location":{"id":"doi:10.26599/bdma.2025.9020032","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2025.9020032","pdf_url":null,"source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.26599/bdma.2025.9020032","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100375105","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-1727-6321"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Liu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036505077","display_name":"Lizong Zhang","orcid":"https://orcid.org/0000-0002-0719-9556"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizong Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenpeng Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenpeng Cao","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011332263","display_name":"Yinong Shi","orcid":"https://orcid.org/0000-0003-2603-0497"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinong Shi","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055707628","display_name":"Chong Mu","orcid":"https://orcid.org/0000-0001-6372-6843"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chong Mu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China,Chengdu,China,611731","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008956810","display_name":"Jiaxin Li","orcid":"https://orcid.org/0000-0002-4790-3173"},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxin Li","raw_affiliation_strings":["Miaozhendida (Beijing) Network Technology Co. Ltd.,Beijing,China,100085"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Miaozhendida (Beijing) Network Technology Co. Ltd.,Beijing,China,100085","institution_ids":["https://openalex.org/I6507939"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100375105"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":1.0875,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81833282,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"8","issue":"6","first_page":"1418","last_page":"1431"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9979000091552734,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9818000197410583,"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/question-answering","display_name":"Question answering","score":0.7462000250816345},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5404999852180481},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5371999740600586},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5271999835968018},{"id":"https://openalex.org/keywords/implicit-knowledge","display_name":"Implicit knowledge","score":0.4593999981880188},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44359999895095825},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.40700000524520874},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.39910000562667847},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3709999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506999969482422},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7462000250816345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6060000061988831},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5889000296592712},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5404999852180481},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5371999740600586},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C2986065213","wikidata":"https://www.wikidata.org/wiki/Q743861","display_name":"Implicit knowledge","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44359999895095825},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36980000138282776},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.31040000915527344},{"id":"https://openalex.org/C124469403","wikidata":"https://www.wikidata.org/wiki/Q1813993","display_name":"Procedural knowledge","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26599/bdma.2025.9020032","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2025.9020032","pdf_url":null,"source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d43d98a0f9a247ff8ae1168a18314fc6","is_oa":true,"landing_page_url":"https://doaj.org/article/d43d98a0f9a247ff8ae1168a18314fc6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data Mining and Analytics, Vol 8, Iss 6, Pp 1418-1431 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.26599/bdma.2025.9020032","is_oa":true,"landing_page_url":"https://doi.org/10.26599/bdma.2025.9020032","pdf_url":null,"source":{"id":"https://openalex.org/S4210209060","display_name":"Big Data Mining and Analytics","issn_l":"2096-0654","issn":["2096-0654"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311901","host_organization_name":"Tsinghua University Press","host_organization_lineage":["https://openalex.org/P4310311901"],"host_organization_lineage_names":["Tsinghua University Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data Mining and Analytics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7835629999","display_name":null,"funder_award_id":"62271125","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2891394954","https://openalex.org/W2947312908","https://openalex.org/W2964303913","https://openalex.org/W3093200502","https://openalex.org/W3099655892","https://openalex.org/W3139224848","https://openalex.org/W3155855665","https://openalex.org/W3156470785","https://openalex.org/W3172845486","https://openalex.org/W3199693760","https://openalex.org/W3207493267","https://openalex.org/W4226321975","https://openalex.org/W4226452284","https://openalex.org/W4252076394","https://openalex.org/W4281609631","https://openalex.org/W4287891464","https://openalex.org/W4312846625","https://openalex.org/W4312971273","https://openalex.org/W4385567149","https://openalex.org/W4385570045","https://openalex.org/W4385572364","https://openalex.org/W4385574156","https://openalex.org/W4385574177","https://openalex.org/W4386065596","https://openalex.org/W4386076140","https://openalex.org/W4388973540","https://openalex.org/W4391707526","https://openalex.org/W4392079948","https://openalex.org/W4392353733","https://openalex.org/W4392504399","https://openalex.org/W4400076876","https://openalex.org/W4400381467","https://openalex.org/W4401043863","https://openalex.org/W4401979966","https://openalex.org/W4404782964","https://openalex.org/W4405021939"],"related_works":[],"abstract_inverted_index":{"Knowledge-based":[0],"Visual":[1],"Question":[2],"Answering":[3],"(VQA)":[4],"is":[5],"a":[6,91,168],"challenging":[7],"task":[8],"that":[9,61,182],"requires":[10],"models":[11],"to":[12,31,99,109,123],"access":[13],"external":[14],"knowledge":[15,34,47,97,105,127,134],"for":[16,26,94,129,160],"reasoning.":[17],"Large":[18],"Language":[19,88],"Models":[20,89],"(LLMs)":[21],"have":[22],"recently":[23],"been":[24],"employed":[25],"zero-shot":[27,101,188],"knowledge-based":[28,102,189],"VQA":[29,190],"due":[30],"their":[32,50,115],"inherent":[33],"storage":[35],"and":[36,49,52,72,113,147,156,176],"in-context":[37,53,65],"learning":[38,54,66],"capabilities.":[39],"However,":[40],"LLMs":[41],"are":[42,151,172],"commonly":[43],"perceived":[44],"as":[45,139],"implicit":[46],"bases,":[48],"generative":[51],"potential":[55],"remains":[56],"underutilized.":[57],"Existing":[58],"works":[59],"demonstrate":[60],"the":[62,70,120,145],"performance":[63],"of":[64,74,80,149,158,170],"strongly":[67],"depends":[68],"on":[69,153,174],"quality":[71,157],"order":[73],"demonstrations":[75,112,150,159],"in":[76],"prompts.":[77],"In":[78,142],"light":[79],"this,":[81],"we":[82],"propose":[83],"Knowledge":[84],"Generation":[85],"with":[86],"Frozen":[87],"(KGFLM),":[90],"novel":[92],"method":[93,184],"generating":[95],"explicit":[96],"statements":[98,128,135],"improve":[100],"VQA.":[103],"Our":[104],"generation":[106],"strategy":[107],"aims":[108],"identify":[110],"effective":[111],"determine":[114],"optimal":[116],"order,":[117],"thereby":[118],"activating":[119],"frozen":[121],"LLM":[122],"produce":[124],"more":[125],"useful":[126],"better":[130],"predictions.":[131],"The":[132,179],"generated":[133],"can":[136],"also":[137],"serve":[138],"interpretable":[140],"rationales.":[141],"our":[143,183],"method,":[144],"selection":[146],"arrangement":[148],"based":[152],"semantic":[154],"similarity":[155],"each":[161],"question,":[162],"without":[163],"requiring":[164],"additional":[165],"annotations.":[166],"Furthermore,":[167],"series":[169],"experiments":[171],"conducted":[173],"A-OKVQA":[175],"OKVQA":[177],"datasets.":[178],"results":[180],"show":[181],"outperforms":[185],"some":[186],"superior":[187],"methods.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}