{"id":"https://openalex.org/W4417128654","doi":"https://doi.org/10.18653/v1/2026.acl-long.116","title":"SDE-SQL: Enhancing Text-to-SQL Generation in Large Language Models via Self-Driven Exploration with SQL Probes","display_name":"SDE-SQL: Enhancing Text-to-SQL Generation in Large Language Models via Self-Driven Exploration with SQL Probes","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417128654","doi":"https://doi.org/10.18653/v1/2026.acl-long.116"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.116","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.116","pdf_url":"https://aclanthology.org/2026.acl-long.116.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.116.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101630302","display_name":"Wenxuan Xie","orcid":"https://orcid.org/0009-0005-1979-1564"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxuan Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066710415","display_name":"Yaxun Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaxun Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024453719","display_name":"Wenhao Jiang","orcid":"https://orcid.org/0000-0002-0795-366X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhao Jiang","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":20.1957,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96577405,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2507","last_page":"2525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3070000112056732,"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":0.3070000112056732,"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":0.25130000710487366,"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/T14347","display_name":"Big Data and Digital Economy","score":0.034299999475479126,"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/sql","display_name":"SQL","score":0.6610000133514404},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.579800009727478},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.578000009059906},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5716000199317932},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5436000227928162},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4611999988555908},{"id":"https://openalex.org/keywords/data-definition-language","display_name":"Data definition language","score":0.3497999906539917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.852400004863739},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6610000133514404},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.579800009727478},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.578000009059906},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5716000199317932},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5436000227928162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4733999967575073},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4611999988555908},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43880000710487366},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4316999912261963},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.40470001101493835},{"id":"https://openalex.org/C55596503","wikidata":"https://www.wikidata.org/wiki/Q1431648","display_name":"Data definition language","level":3,"score":0.3497999906539917},{"id":"https://openalex.org/C154420247","wikidata":"https://www.wikidata.org/wiki/Q846619","display_name":"Stored procedure","level":5,"score":0.3257000148296356},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.257999986410141}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.116","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.116","pdf_url":"https://aclanthology.org/2026.acl-long.116.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.07245","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.07245","pdf_url":"https://arxiv.org/pdf/2506.07245","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,"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.2506.07245","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.07245","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.116","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.116","pdf_url":"https://aclanthology.org/2026.acl-long.116.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417128654.pdf","grobid_xml":"https://content.openalex.org/works/W4417128654.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,113,135],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"have":[7],"led":[8],"to":[9,34,49,57,76,97],"substantial":[10],"progress":[11],"on":[12,20,124],"the":[13,31,37,41,55,62,87,95,107,125,139],"Text-to-SQL":[14],"task.However,":[15],"existing":[16],"approaches":[17],"typically":[18],"depend":[19],"static,":[21],"preprocessed":[22],"database":[23,39],"information":[24,100],"supplied":[25],"at":[26],"inference":[27],"time,":[28],"which":[29],"restricts":[30],"model's":[32],"capacity":[33],"deeply":[35],"comprehend":[36],"underlying":[38],"content.In":[40],"absence":[42],"of":[43,80,91,106],"dynamic":[44],"interaction,":[45],"LLMs":[46,75],"are":[47],"limited":[48],"fixed,":[50],"humancurated":[51],"context":[52],"and":[53,89,101],"lack":[54],"ability":[56],"autonomously":[58],"query":[59],"or":[60,121,153],"explore":[61],"data.To":[63],"overcome":[64],"this":[65],"limitation,":[66],"we":[67],"introduce":[68],"SDE-SQL,":[69],"a":[70,114,143],"novel":[71],"framework":[72],"that":[73],"empowers":[74],"perform":[77],"Self-Driven":[78],"Exploration":[79],"databases":[81],"during":[82],"inference.This":[83],"is":[84,168],"achieved":[85],"through":[86],"generation":[88],"execution":[90,136],"SQL":[92],"probes,":[93],"enabling":[94],"model":[96,154],"actively":[98],"retrieve":[99],"iteratively":[102],"refine":[103],"its":[104],"understanding":[105],"database.Unlike":[108],"prior":[109],"methods,":[110],"SDE-SQL":[111,160],"operates":[112],"zero-shot":[115],"setting,":[116],"requiring":[117],"no":[118],"in-context":[119],"demonstrations":[120],"question-SQL":[122],"pairs.Evaluated":[123],"BIRD":[126],"benchmark":[127],"with":[128,158],"Qwen2.5-72B-Instruct,SDE-SQL":[129],"achieves":[130],"an":[131,162],"8.02%":[132],"relative":[133],"improvement":[134],"accuracy":[137],"over":[138],"vanilla":[140],"Qwen2.5-72B-Instructbaseline,":[141],"establishing":[142],"new":[144],"state-of-the-art":[145],"among":[146],"open-source":[147],"methods":[148],"without":[149],"supervised":[150],"fine-tuning":[151],"(SFT)":[152],"ensembling.Furthermore,":[155],"when":[156],"combined":[157],"SFT,":[159],"delivers":[161],"additional":[163],"0.52%":[164],"performance":[165],"gain.Our":[166],"code":[167],"publicly":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}