{"id":"https://openalex.org/W4412888518","doi":"https://doi.org/10.18653/v1/2025.findings-acl.443","title":"SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs","display_name":"SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888518","doi":"https://doi.org/10.18653/v1/2025.findings-acl.443"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.443","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.443","pdf_url":"https://aclanthology.org/2025.findings-acl.443.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: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.443.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112107646","display_name":"Guo Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Dong Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107997514","display_name":"S. Ye","orcid":"https://orcid.org/0000-0002-7864-4282"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shenghao Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113402468","display_name":"S. Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuangwu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181437","display_name":"Jianyang Jianyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianyang Jianyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101795875","display_name":"Xiaobin Tan","orcid":"https://orcid.org/0000-0001-6483-2840"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaobin Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8441","last_page":"8452"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.920199990272522,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9132000207901001,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7304251194000244},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6956052780151367},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33312007784843445},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32774773240089417},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3134893476963043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304251194000244},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6956052780151367},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33312007784843445},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32774773240089417},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3134893476963043}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.443","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.443","pdf_url":"https://aclanthology.org/2025.findings-acl.443.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: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.13725","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.13725","pdf_url":"https://arxiv.org/pdf/2505.13725","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"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.443","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.443","pdf_url":"https://aclanthology.org/2025.findings-acl.443.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087663138","display_name":null,"funder_award_id":"2024YDLN0004","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888518.pdf","grobid_xml":"https://content.openalex.org/works/W4412888518.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"Language":[1],"models":[2,21,92,104],"(LLMs)":[3],"have":[4],"demonstrated":[5],"significant":[6],"potential":[7],"in":[8,44,100],"text-to-SQL":[9,42],"reasoning":[10,43],"tasks,":[11],"yet":[12],"a":[13,31,88,101],"substantial":[14],"performance":[15,110,140],"gap":[16,141],"persists":[17],"between":[18],"existing":[19],"open-source":[20,91],"and":[22,37,53,63,72,96,116,132],"their":[23],"closed-source":[24,143],"counterparts.In":[25],"this":[26],"paper,":[27],"we":[28,86],"introduce":[29],"SQLForge,":[30],"novel":[32],"approach":[33],"for":[34],"synthesizing":[35],"reliable":[36],"diverse":[38],"data":[39,47,58,74,80],"to":[40,78],"enhance":[41],"LLMs.We":[45],"improve":[46],"reliability":[48],"through":[49],"SQL":[50,69],"syntax":[51],"constraints":[52],"SQL-to-question":[54],"reverse":[55],"translation,":[56],"ensuring":[57],"logic":[59],"at":[60],"both":[61],"structural":[62],"semantic":[64],"levels.We":[65],"also":[66],"propose":[67],"an":[68],"template":[70],"enrichment":[71],"iterative":[73],"domain":[75],"exploration":[76],"mechanism":[77],"boost":[79],"diversity.Building":[81],"on":[82,111,129,134],"the":[83,108,112,120,139],"augmented":[84],"data,":[85],"fine-tune":[87],"variety":[89],"of":[90,103,127],"with":[93,142],"different":[94],"architectures":[95],"parameter":[97],"sizes,":[98],"resulting":[99],"family":[102],"termed":[105],"SQLForge-LM.SQLForge-LM":[106],"achieves":[107,124],"state-of-theart":[109],"widely":[113],"recognized":[114],"Spider":[115,130],"BIRD":[117,135],"benchmarks":[118],"among":[119],"opensource":[121],"models.Specifically,":[122],"SQLForge-LM":[123],"EX":[125],"accuracy":[126],"85.7%":[128],"Dev":[131],"59.8%":[133],"Dev,":[136],"significantly":[137],"narrowing":[138],"methods.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-08-04T00:00:00"}