{"id":"https://openalex.org/W4396571402","doi":"https://doi.org/10.14778/3641204.3641221","title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","display_name":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4396571402","doi":"https://doi.org/10.14778/3641204.3641221"},"language":"en","primary_location":{"id":"doi:10.14778/3641204.3641221","doi":"https://doi.org/10.14778/3641204.3641221","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3641204.3641221","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-b","norway-2","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.15363","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103243413","display_name":"Dawei Gao","orcid":"https://orcid.org/0009-0007-3882-5189","observed_orcids":["https://orcid.org/0009-0007-3882-5189"]},"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":"Dawei Gao","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408835","display_name":"Haibin Wang","orcid":"https://orcid.org/0000-0002-9269-1229","observed_orcids":["https://orcid.org/0000-0002-9269-1229","https://orcid.org/0009-0009-3763-2128"]},"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":"Haibin Wang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046576694","display_name":"Yaliang Li","orcid":"https://orcid.org/0000-0002-4204-6096","observed_orcids":["https://orcid.org/0000-0002-4204-6096"]},"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":"Yaliang Li","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102803552","display_name":"Xiuyu Sun","orcid":"https://orcid.org/0000-0002-7208-8078","observed_orcids":["https://orcid.org/0000-0002-7208-8078"]},"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":"Xiuyu Sun","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112991087","display_name":"Yichen Qian","orcid":"https://orcid.org/0000-0002-3931-0108","observed_orcids":["https://orcid.org/0000-0002-3931-0108"]},"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":"Yichen Qian","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040297543","display_name":"Bolin Ding","orcid":"https://orcid.org/0000-0003-1535-9692","observed_orcids":["https://orcid.org/0000-0003-1535-9692"]},"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":"Bolin Ding","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057864403","display_name":"Jingren Zhou","orcid":"https://orcid.org/0000-0002-4220-2634","observed_orcids":["https://orcid.org/0000-0002-4220-2634"]},"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":"Jingren Zhou","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":76.9955,"has_fulltext":true,"cited_by_count":746,"citation_normalized_percentile":{"value":0.99954714,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"17","issue":"5","first_page":"1132","last_page":"1145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6410999894142151,"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/T10028","display_name":"Topic Modeling","score":0.6410999894142151,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.1648000031709671,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.05860000103712082,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/text-to-sql","display_name":"text-to-SQL","score":0.9319999814033508},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9990000128746033},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.8709999918937683},{"id":"https://openalex.org/keywords/spider-benchmark","display_name":"Spider benchmark","score":0.8759999871253967},{"id":"https://openalex.org/keywords/example-selection","display_name":"example selection","score":0.6740000247955322},{"id":"https://openalex.org/keywords/question-representation","display_name":"question representation","score":0.7919999957084656},{"id":"https://openalex.org/keywords/open-source-llms","display_name":"open-source LLMs","score":0.7260000109672546},{"id":"https://openalex.org/keywords/supervised-fine-tuning","display_name":"supervised fine-tuning","score":0.996999979019165},{"id":"https://openalex.org/keywords/token-efficiency","display_name":"token efficiency","score":0.9800000190734863},{"id":"https://openalex.org/keywords/benchmark-evaluation","display_name":"benchmark evaluation","score":0.5609999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581311464309692},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7154086828231812},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5926403403282166},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5450004935264587},{"id":"https://openalex.org/C55596503","wikidata":"https://www.wikidata.org/wiki/Q1431648","display_name":"Data definition language","level":3,"score":0.4402525722980499},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38105064630508423},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36123913526535034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34659528732299805},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07044801115989685},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/3641204.3641221","doi":"https://doi.org/10.14778/3641204.3641221","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3641204.3641221","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-b","norway-2","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2308.15363","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.15363","pdf_url":"https://arxiv.org/pdf/2308.15363","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2308.15363","doi":"https://doi.org/10.48550/arxiv.2308.15363","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2308.15363","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.15363","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.15363","pdf_url":"https://arxiv.org/pdf/2308.15363","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396571402.pdf","grobid_xml":"https://content.openalex.org/works/W4396571402.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2606555609","https://openalex.org/W2607303097","https://openalex.org/W2781528640","https://openalex.org/W2890585661","https://openalex.org/W2985377636","https://openalex.org/W3035231859","https://openalex.org/W3086973390","https://openalex.org/W3093819145","https://openalex.org/W3200285169","https://openalex.org/W4205807230","https://openalex.org/W4226490385","https://openalex.org/W4238216513","https://openalex.org/W4285227295","https://openalex.org/W4285451014","https://openalex.org/W4303105513","https://openalex.org/W4312537169","https://openalex.org/W4317716303","https://openalex.org/W4379468930","https://openalex.org/W4386185625"],"related_works":["https://openalex.org/W4399795137","https://openalex.org/W4392627821","https://openalex.org/W4406072772","https://openalex.org/W7134954916","https://openalex.org/W4379258895","https://openalex.org/W4404467346","https://openalex.org/W4402670728","https://openalex.org/W4403942854","https://openalex.org/W7168286540","https://openalex.org/W4403344290"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"emerged":[5],"as":[6,126,128],"a":[7,17,42,77,94,168],"new":[8,78,95],"paradigm":[9],"for":[10],"Text-to-SQL":[11,30,144,172],"task.":[12],"However,":[13],"the":[14,21,85,99,129,134,148,156],"absence":[15],"of":[16,23,101,133,171],"systematical":[18,43],"benchmark":[19],"inhibits":[20],"development":[22],"designing":[24],"effective,":[25],"efficient":[26,140],"and":[27,44,57,60,69,92,110,131,141,154,175,179],"economic":[28,142],"LLM-based":[29,143],"solutions.":[31],"To":[32,97],"address":[33],"this":[34,37,160],"challenge,":[35],"in":[36,107,124,151],"paper,":[38],"we":[39,65,75,104,146],"first":[40],"conduct":[41],"extensive":[45],"comparison":[46],"over":[47],"existing":[48],"prompt":[49,152],"engineering":[50,153],"methods,":[51],"including":[52],"question":[53],"representation,":[54],"example":[55,58],"selection":[56],"organization,":[59],"with":[61,88,115,173],"these":[62,73],"experimental":[63],"results,":[64],"elaborate":[66],"their":[67,113],"pros":[68],"cons.":[70],"Based":[71],"on":[72],"findings,":[74],"propose":[76],"integrated":[79],"solution,":[80,145],"named":[81],"DAIL-SQL,":[82],"which":[83],"refreshes":[84],"Spider":[86],"leaderboard":[87],"86.6%":[89],"execution":[90],"accuracy":[91],"sets":[93],"bar.":[96],"explore":[98],"potential":[100,123],"open-source":[102,121],"LLM,":[103],"investigate":[105],"them":[106],"various":[108],"scenarios,":[109],"further":[111,177],"enhance":[112],"performance":[114],"supervised":[116,135],"fine-tuning.":[117,136],"Our":[118],"explorations":[119],"highlight":[120],"LLMs'":[122],"Text-to-SQL,":[125],"well":[127],"advantages":[130],"disadvantages":[132],"Additionally,":[137],"towards":[138],"an":[139],"emphasize":[147],"token":[149],"efficiency":[150],"compare":[155],"prior":[157],"studies":[158],"under":[159],"metric.":[161],"We":[162],"hope":[163],"that":[164],"our":[165],"work":[166],"provides":[167],"deeper":[169],"understanding":[170],"LLMs,":[174],"inspires":[176],"investigations":[178],"broad":[180],"applications.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":346},{"year":2025,"cited_by_count":283},{"year":2024,"cited_by_count":107},{"year":2023,"cited_by_count":10}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2024-05-03T00:00:00"}