{"id":"https://openalex.org/W4406072772","doi":"https://doi.org/10.1145/3737873","title":"A Survey on Employing Large Language Models for Text-to-SQL Tasks","display_name":"A Survey on Employing Large Language Models for Text-to-SQL Tasks","publication_year":2025,"publication_date":"2025-06-03","ids":{"openalex":"https://openalex.org/W4406072772","doi":"https://doi.org/10.1145/3737873"},"language":"en","primary_location":{"id":"doi:10.1145/3737873","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3737873","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.15186","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Liang Shi","orcid":"https://orcid.org/0009-0009-3726-0299"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Shi","raw_affiliation_strings":["School of Computer Science, Peking University"],"raw_orcid":"https://orcid.org/0009-0009-3726-0299","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101554113","display_name":"Zhengju Tang","orcid":"https://orcid.org/0009-0001-9299-2662"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengju Tang","raw_affiliation_strings":["School of Computer Science, Peking University"],"raw_orcid":"https://orcid.org/0009-0001-9299-2662","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nan Zhang","orcid":"https://orcid.org/0009-0006-3678-5059"},"institutions":[{"id":"https://openalex.org/I2799881413","display_name":"Zen-Noh (Japan)","ror":"https://ror.org/05cwghy20","country_code":"JP","type":"company","lineage":["https://openalex.org/I2799881413"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nan Zhang","raw_affiliation_strings":["ZettaData US"],"raw_orcid":"https://orcid.org/0009-0006-3678-5059","affiliations":[{"raw_affiliation_string":"ZettaData US","institution_ids":["https://openalex.org/I2799881413"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaotong Zhang","orcid":"https://orcid.org/0009-0000-2725-2927"},"institutions":[{"id":"https://openalex.org/I4210126929","display_name":"CE Technologies (United Kingdom)","ror":"https://ror.org/02pw67e25","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210126929"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaotong Zhang","raw_affiliation_strings":["Beijing Bytedance Technology Co Ltd"],"raw_orcid":"https://orcid.org/0009-0000-2725-2927","affiliations":[{"raw_affiliation_string":"Beijing Bytedance Technology Co Ltd","institution_ids":["https://openalex.org/I4210126929"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhi Yang","orcid":"https://orcid.org/0000-0002-8219-4499"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Yang","raw_affiliation_strings":["School of Computer Science, Peking University"],"raw_orcid":"https://orcid.org/0000-0002-8219-4499","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":36.9342,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.99691137,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"58","issue":"2","first_page":"1","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7612000107765198,"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":0.7612000107765198,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.6934000253677368,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.6646000146865845,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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":0.7299051880836487},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.5900370478630066},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4467660188674927},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4452138841152191},{"id":"https://openalex.org/keywords/data-definition-language","display_name":"Data definition language","score":0.44016608595848083},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3814864158630371}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7299051880836487},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5900370478630066},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4467660188674927},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4452138841152191},{"id":"https://openalex.org/C55596503","wikidata":"https://www.wikidata.org/wiki/Q1431648","display_name":"Data definition language","level":3,"score":0.44016608595848083},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3814864158630371}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3737873","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3737873","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2407.15186","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.15186","pdf_url":"https://arxiv.org/pdf/2407.15186","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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.2407.15186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.15186","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.15186","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.15186","pdf_url":"https://arxiv.org/pdf/2407.15186","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406072772.pdf","grobid_xml":"https://content.openalex.org/works/W4406072772.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W4389519605","https://openalex.org/W2952032096","https://openalex.org/W4405740197","https://openalex.org/W3015937477","https://openalex.org/W3093819145","https://openalex.org/W3095319910","https://openalex.org/W4389524074","https://openalex.org/W4205991051","https://openalex.org/W2269738476","https://openalex.org/W4290927888","https://openalex.org/W4280534475","https://openalex.org/W4285247752","https://openalex.org/W4389523875","https://openalex.org/W4391555793","https://openalex.org/W3086973390","https://openalex.org/W4393065402","https://openalex.org/W3102020135"],"related_works":["https://openalex.org/W1592149428","https://openalex.org/W650213220","https://openalex.org/W1980548249","https://openalex.org/W4320802139","https://openalex.org/W3092022493","https://openalex.org/W2183714398","https://openalex.org/W2042813897","https://openalex.org/W2340883001","https://openalex.org/W4382050951","https://openalex.org/W2079321164"],"abstract_inverted_index":{"With":[0],"the":[1,4,37,63,80],"development":[2],"of":[3,12,24,62],"Large":[5],"Language":[6],"Models":[7],"(LLMs),":[8],"a":[9,21,47],"large":[10],"range":[11],"LLM-based":[13,25],"Text-to-SQL(Text2SQL)":[14],"methods":[15,65],"have":[16],"emerged.":[17],"This":[18],"survey":[19],"provides":[20],"comprehensive":[22,48],"review":[23],"Text2SQL":[26],"studies.":[27],"We":[28,57],"first":[29],"enumerate":[30],"classic":[31],"benchmarks":[32],"and":[33,43,50,66,73,82],"evaluation":[34],"metrics.":[35],"For":[36],"two":[38],"mainstream":[39],"methods,":[40],"prompt":[41],"engineering":[42],"finetuning,":[44],"we":[45,78],"introduce":[46],"taxonomy":[49],"offer":[51],"practical":[52],"insights":[53],"into":[54],"each":[55],"subcategory.":[56],"present":[58],"an":[59],"overall":[60],"analysis":[61],"above":[64],"various":[67],"models":[68],"evaluated":[69],"on":[70],"well-known":[71],"datasets":[72],"extract":[74],"some":[75],"characteristics.":[76],"Finally,":[77],"discuss":[79],"challenges":[81],"future":[83],"directions":[84],"in":[85],"this":[86],"field.":[87]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":10}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-01-05T00:00:00"}