{"id":"https://openalex.org/W4404782331","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.84","title":"Diversify, Rationalize, and Combine: Ensembling Multiple QA Strategies for Zero-shot Knowledge-based VQA","display_name":"Diversify, Rationalize, and Combine: Ensembling Multiple QA Strategies for Zero-shot Knowledge-based VQA","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404782331","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.84"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.84","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-emnlp.84","pdf_url":"https://aclanthology.org/2024.findings-emnlp.84.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-emnlp.84.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060751522","display_name":"Miaoyu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Miaoyu Li","raw_affiliation_strings":["College of Computing and Data Science , Nanyang Technological University , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science , Nanyang Technological University , Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047822283","display_name":"Haoxin Li","orcid":"https://orcid.org/0000-0003-2320-4797"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haoxin Li","raw_affiliation_strings":["College of Computing and Data Science , Nanyang Technological University , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science , Nanyang Technological University , Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049430074","display_name":"Zilin Du","orcid":"https://orcid.org/0000-0003-3534-9547"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zilin Du","raw_affiliation_strings":["College of Computing and Data Science , Nanyang Technological University , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science , Nanyang Technological University , Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002351613","display_name":"Boyang Li","orcid":"https://orcid.org/0000-0002-0080-8857"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Boyang Li","raw_affiliation_strings":["College of Computing and Data Science , Nanyang Technological University , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science , Nanyang Technological University , Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":2.4863,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.90869861,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1552","last_page":"1566"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.8105999827384949,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.8105999827384949,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.7184000015258789,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11357","display_name":"Risk and Safety Analysis","score":0.6944000124931335,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6818926930427551},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6406859159469604},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.5657467842102051},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5143235921859741},{"id":"https://openalex.org/keywords/zero-knowledge-proof","display_name":"Zero-knowledge proof","score":0.4557478129863739},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39150363206863403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37107476592063904},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.161601722240448},{"id":"https://openalex.org/keywords/cryptography","display_name":"Cryptography","score":0.10390892624855042},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.055908918380737305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6818926930427551},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6406859159469604},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.5657467842102051},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5143235921859741},{"id":"https://openalex.org/C176329583","wikidata":"https://www.wikidata.org/wiki/Q191943","display_name":"Zero-knowledge proof","level":3,"score":0.4557478129863739},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39150363206863403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37107476592063904},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.161601722240448},{"id":"https://openalex.org/C178489894","wikidata":"https://www.wikidata.org/wiki/Q8789","display_name":"Cryptography","level":2,"score":0.10390892624855042},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.055908918380737305},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-emnlp.84","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-emnlp.84","pdf_url":"https://aclanthology.org/2024.findings-emnlp.84.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.84","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.findings-emnlp.84","pdf_url":"https://aclanthology.org/2024.findings-emnlp.84.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6597490799","display_name":null,"funder_award_id":"NRF-NRFF13-2021-0006","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404782331.pdf","grobid_xml":"https://content.openalex.org/works/W4404782331.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2952570804","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469"],"abstract_inverted_index":{"Knowledge-based":[0,39],"Visual":[1],"Qustion-answering":[2],"(K-VQA)":[3],"often":[4,23],"requires":[5],"the":[6,12,84,88,99,106,112,133,136],"use":[7],"of":[8,46,58,148],"background":[9],"knowledge":[10,19],"beyond":[11],"image.However,":[13],"we":[14,31],"discover":[15],"that":[16,116,132],"a":[17,44],"single":[18],"generation":[20],"strategy":[21],"is":[22,141],"insufficient":[24],"for":[25,38,91],"all":[26],"K-VQA":[27],"questions.To":[28],"this":[29],"end,":[30],"propose":[32],"Diversification,":[33],"Evidence":[34],"Truncation,":[35],"and":[36,50,63,87,127,131,152],"Combination":[37],"Elucidation":[40],"(DIETCOKE),":[41],"which":[42],"utilizes":[43],"bundle":[45],"complementary":[47],"question-answering":[48],"tactics":[49],"aggregates":[51],"their":[52],"answers":[53],"using":[54,95],"textual":[55],"rationales.DIETCOKE":[56],"comprises":[57],"three":[59,68,113],"stages:":[60],"diversification,":[61],"rationalization,":[62],"ensemble.The":[64],"diversification":[65],"stage":[66,80],"generates":[67,81],"distinctive":[69],"decision":[70],"contexts,":[71],"each":[72,92],"leading":[73],"to":[74,160],"its":[75],"own":[76],"answer":[77,93,110],"candidate.The":[78],"rationalization":[79],"two":[82],"rationales,":[83],"automatic":[85],"rationale":[86],"mechanistic":[89],"rationale,":[90],"candidate":[94],"decorrelated":[96],"techniques.Finally,":[97],"in":[98,135],"ensemble":[100],"stage,":[101],"an":[102],"LLM":[103],"informed":[104],"by":[105,123],"rationales":[107],"selects":[108],"one":[109],"from":[111],"candidates.Experiments":[114],"show":[115],"DIETCOKE":[117],"significantly":[118],"outperforms":[119],"state-of-the-art":[120],"LLM-based":[121],"baselines":[122],"2.8%":[124],"on":[125,129],"OK-VQA":[126],"4.7%":[128],"A-OKVQA":[130],"strategies":[134],"ensembles":[137],"are":[138],"highly":[139],"complementary.Code":[140],"available":[142],"at:":[143],"https://github.com/limiaoyu/DietCokeCaptions:":[144],"A":[145],"three-plated":[146],"meal":[147],"soup":[149],"with":[150],"bread":[151],"muffins...":[153],"Prediction:":[154],"Muffin":[155],"Short-form":[156],"Knowledge:":[157,169],"Soups":[158,171],"tend":[159],"have":[161],"fewer":[162,173],"carbs":[163,174],"than":[164],"other":[165],"food.Prediction:":[166],"Soup":[167],"Long-form":[168],"...":[170],"contain":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}
