{"id":"https://openalex.org/W4387968292","doi":"https://doi.org/10.1145/3581783.3612389","title":"Improving Zero-shot Visual Question Answering via Large Language Models with Reasoning Question Prompts","display_name":"Improving Zero-shot Visual Question Answering via Large Language Models with Reasoning Question Prompts","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968292","doi":"https://doi.org/10.1145/3581783.3612389"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612389","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612389","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612389","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612389","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090588589","display_name":"Yunshi Lan","orcid":"https://orcid.org/0000-0002-0192-8498"},"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":"Yunshi Lan","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0192-8498","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101546842","display_name":"Xiang Li","orcid":"https://orcid.org/0009-0000-8818-0269"},"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":"Xiang Li","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-8818-0269","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103015399","display_name":"Xin Liu","orcid":"https://orcid.org/0009-0004-0341-3860"},"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":"Xin Liu","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-0341-3860","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015845161","display_name":"Yang Li","orcid":"https://orcid.org/0000-0003-4155-2859"},"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":"Yang Li","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4155-2859","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733317","display_name":"Wei Qin","orcid":"https://orcid.org/0000-0002-9513-4372"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Qin","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9513-4372","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089931216","display_name":"Weining Qian","orcid":"https://orcid.org/0000-0002-4132-8630"},"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":"Weining Qian","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4132-8630","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"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":true,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4389","last_page":"4400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9926999807357788,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9670000076293945,"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/computer-science","display_name":"Computer science","score":0.5982642769813538},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5567424893379211},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5535755157470703},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5357809066772461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5273975729942322},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49286890029907227},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.48011279106140137},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4539366662502289},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.4288586378097534},{"id":"https://openalex.org/keywords/premise","display_name":"Premise","score":0.4167959690093994},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23857805132865906},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20088112354278564},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.15527638792991638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5982642769813538},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5567424893379211},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5535755157470703},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5357809066772461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5273975729942322},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49286890029907227},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.48011279106140137},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4539366662502289},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.4288586378097534},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.4167959690093994},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23857805132865906},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20088112354278564},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.15527638792991638},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612389","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612389","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612389","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612389","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612389","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612389","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3854025682","display_name":null,"funder_award_id":"62206097","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968292.pdf","grobid_xml":"https://content.openalex.org/works/W4387968292.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1933349210","https://openalex.org/W2560730294","https://openalex.org/W2607303097","https://openalex.org/W2947312908","https://openalex.org/W2963644680","https://openalex.org/W2966746916","https://openalex.org/W3034886066","https://openalex.org/W3035454069","https://openalex.org/W3101703188","https://openalex.org/W3114427170","https://openalex.org/W3153427360","https://openalex.org/W3166846774","https://openalex.org/W3172845486","https://openalex.org/W3173220247","https://openalex.org/W3174770825","https://openalex.org/W3176821361","https://openalex.org/W3196731672","https://openalex.org/W3199693760","https://openalex.org/W3207493267","https://openalex.org/W4220993274","https://openalex.org/W4226271114","https://openalex.org/W4226452284","https://openalex.org/W4285191490","https://openalex.org/W4285225959","https://openalex.org/W4285300583","https://openalex.org/W4287887134","https://openalex.org/W4293261733","https://openalex.org/W4312971273","https://openalex.org/W4385567149","https://openalex.org/W4385574005","https://openalex.org/W4386065596","https://openalex.org/W4386075505","https://openalex.org/W4386076140","https://openalex.org/W4386566765"],"related_works":["https://openalex.org/W590788508","https://openalex.org/W4235873430","https://openalex.org/W2611974471","https://openalex.org/W4313233093","https://openalex.org/W2358082531","https://openalex.org/W2589976903","https://openalex.org/W2335596023","https://openalex.org/W2026719400","https://openalex.org/W2374273535","https://openalex.org/W4225892616"],"abstract_inverted_index":{"Zero-shot":[0],"Visual":[1],"Question":[2,118],"Answering":[3],"(VQA)":[4],"is":[5,37,243],"a":[6,176],"prominent":[7],"vision-language":[8],"task":[9],"that":[10,215],"examines":[11],"both":[12],"the":[13,22,30,76,84,92,127,167,170,182,200,220],"visual":[14],"and":[15,39,106,158,198,227],"textual":[16],"understanding":[17],"capability":[18,50],"of":[19,24,94,129,169,178,222,236],"systems":[20],"in":[21,100,131,175],"absence":[23],"training":[25],"data.":[26],"Recently,":[27],"by":[28],"converting":[29],"images":[31],"into":[32,196],"captions,":[33],"information":[34],"across":[35],"multi-modalities":[36],"bridged":[38],"Large":[40],"Language":[41],"Models":[42],"(LLMs)":[43],"can":[44,124,217],"apply":[45],"their":[46,187],"strong":[47],"zero-shot":[48,132,225,231],"generalization":[49],"to":[51,69,82],"unseen":[52],"questions.":[53],"To":[54,112],"design":[55],"ideal":[56],"prompts":[57,146,207],"for":[58,120,135],"solving":[59],"VQA":[60,101,121,210],"via":[61,147],"LLMs,":[62],"several":[63],"studies":[64],"have":[65],"explored":[66],"different":[67],"strategies":[68],"select":[70],"or":[71],"generate":[72,140],"question-answer":[73],"pairs":[74],"as":[75,143,191],"exemplar":[77],"prompts,":[78],"which":[79,108,123],"guide":[80],"LLMs":[81,130,197,223],"answer":[83,192],"current":[85],"questions":[86,99,142],"effectively.":[87],"However,":[88],"they":[89,216],"totally":[90],"ignore":[91],"role":[93],"question":[95,145,150,163,206],"prompts.":[96],"The":[97],"original":[98,171],"tasks":[102],"usually":[103],"encounter":[104],"ellipses":[105],"ambiguity":[107],"require":[109],"intermediate":[110],"reasoning.":[111],"this":[113],"end,":[114],"we":[115,138],"present":[116],"Reasoning":[117],"Prompts":[119],"tasks,":[122],"further":[125],"activate":[126],"potential":[128],"scenarios.":[133],"Specifically,":[134],"each":[136],"question,":[137],"first":[139],"self-contained":[141],"reasoning":[144,162,205],"an":[148],"unsupervised":[149],"edition":[151],"module":[152],"considering":[153],"sentence":[154],"fluency,":[155],"semantic":[156],"integrity":[157],"syntactic":[159],"invariance.":[160],"Each":[161],"prompt":[164],"clearly":[165],"indicates":[166],"intent":[168],"question.":[172],"This":[173],"results":[174,213,221],"set":[177],"candidate":[179,183],"answers.":[180],"Then,":[181],"answers":[184],"associated":[185],"with":[186],"confidence":[188],"scores":[189],"acting":[190],"heuristics":[193],"are":[194],"fed":[195],"produce":[199],"final":[201],"answer.":[202],"We":[203],"evaluate":[204],"on":[208,224,233],"three":[209,234],"challenges,":[211],"experimental":[212],"demonstrate":[214],"significantly":[218],"improve":[219],"setting":[226],"outperform":[228],"existing":[229],"state-of-the-art":[230],"methods":[232],"out":[235],"four":[237],"data":[238],"sets.":[239],"Our":[240],"source":[241],"code":[242],"publicly":[244],"released":[245],"at":[246],"https://github.com/ECNU-DASE-NLP/RQP.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":7}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}