{"id":"https://openalex.org/W4416035857","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.59","title":"SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning","display_name":"SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035857","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.59"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.59","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.59","pdf_url":"https://aclanthology.org/2025.findings-emnlp.59.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 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.59.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100349344","display_name":"Yuhao Zhang","orcid":"https://orcid.org/0000-0002-1905-7248"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086035676","display_name":"Shaoming Duan","orcid":"https://orcid.org/0000-0002-7546-9562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaoming Duan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000564230","display_name":"Jinhang Su","orcid":"https://orcid.org/0009-0001-4031-1271"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinhang Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103171964","display_name":"Chuanyi Liu","orcid":"https://orcid.org/0000-0002-9846-9709"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuanyi Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101992266","display_name":"Peiyi Han","orcid":"https://orcid.org/0000-0003-0417-4473"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peiyi Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89426848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1092","last_page":"1110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5706999897956848,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.5706999897956848,"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/T10028","display_name":"Topic Modeling","score":0.04450000077486038,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.025200000032782555,"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/parsing","display_name":"Parsing","score":0.49470001459121704},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4083000123500824},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.314300000667572},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3118000030517578},{"id":"https://openalex.org/keywords/bottom-up-parsing","display_name":"Bottom-up parsing","score":0.3077999949455261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7095999717712402},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5906999707221985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5716999769210815},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.49470001459121704},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C60690694","wikidata":"https://www.wikidata.org/wiki/Q894902","display_name":"Bottom-up parsing","level":4,"score":0.3077999949455261},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.59","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.59","pdf_url":"https://aclanthology.org/2025.findings-emnlp.59.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.59","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.59","pdf_url":"https://aclanthology.org/2025.findings-emnlp.59.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4404944658","display_name":null,"funder_award_id":"2023YFB3106504","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7516778469","display_name":null,"funder_award_id":"2024M751555","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"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/W4416035857.pdf","grobid_xml":"https://content.openalex.org/works/W4416035857.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,34,43,52,58,79,101,119,134,138,151],"significant":[2],"advancements":[3],"of":[4,26,46],"selfplay":[5],"fine-tuning":[6,75,91,96,121],"(SPIN),":[7],"which":[8,93],"can":[9],"transform":[10],"a":[11,18,72,88,113],"weak":[12],"large":[13,44],"language":[14],"model":[15,54,109,114,140],"(LLM)":[16],"into":[17],"strong":[19],"one":[20],"through":[21],"competitive":[22],"interactions":[23],"between":[24,143],"models":[25],"varying":[27,117],"capabilities,":[28],"it":[29],"still":[30],"faces":[31],"challenges":[32],"in":[33],"Text-to-SQL":[35,80],"task.SPIN":[36],"does":[37],"not":[38],"generate":[39,63,159],"new":[40,73],"information,":[41],"and":[42,104,146,163,170],"number":[45],"correct":[47,144,160],"SQL":[48,65,145,148],"queries":[49],"produced":[50],"by":[51,150],"opponent":[53,135,152],"during":[55],"self-play":[56,74,120],"reduces":[57],"main":[59,139],"model's":[60],"ability":[61,157],"to":[62,84,107,141,158],"accurate":[64],"queries.To":[66],"address":[67],"this":[68],"challenge,":[69],"we":[70,86,123],"propose":[71,124],"method":[76,128],"tailored":[77],"for":[78],"task,":[81],"called":[82],"SPFT-SQL.Prior":[83],"self-play,":[85],"introduce":[87],"verification-based":[89],"iterative":[90],"approach,":[92],"synthesizes":[94],"high-quality":[95],"data":[97],"iteratively":[98],"based":[99],"on":[100,166],"database":[102],"schema":[103],"validation":[105],"feedback":[106],"enhance":[108],"performance,":[110],"while":[111],"building":[112],"base":[115],"with":[116],"capabilities.During":[118],"phase,":[122],"an":[125],"error-driven":[126],"loss":[127],"that":[129,176],"incentivizes":[130],"incorrect":[131],"outputs":[132],"from":[133],"model,":[136,153],"enabling":[137],"distinguish":[142],"erroneous":[147],"generated":[149],"thereby":[154],"improving":[155],"its":[156],"SQL.Extensive":[161],"experiments":[162],"in-depth":[164],"analyses":[165],"six":[167],"opensource":[168],"LLMs":[169],"five":[171],"widely":[172],"used":[173],"benchmarks":[174],"demonstrate":[175],"our":[177],"approach":[178],"outperforms":[179],"existing":[180],"state-of-the-art":[181],"(SOTA)":[182],"methods.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}