{"id":"https://openalex.org/W4416033985","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1032","title":"DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL","display_name":"DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033985","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1032"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1032","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1032","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1032.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1032.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101872204","display_name":"Hongjun Ma","orcid":"https://orcid.org/0000-0002-8490-5514"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyuan Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004615610","display_name":"Yongliang Shen","orcid":"https://orcid.org/0000-0003-0975-3554"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongliang Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101862760","display_name":"Hengwei Liu","orcid":"https://orcid.org/0000-0003-0231-6562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hengwei Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037725670","display_name":"Wenqi Zhang","orcid":"https://orcid.org/0000-0002-4482-6715"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenqi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029644187","display_name":"Hang Xu","orcid":"https://orcid.org/0000-0002-6685-0230"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haolei Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111154818","display_name":"Qiuying Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiuying Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100712167","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0001-9548-0411"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026310569","display_name":"Weiming L\u00fc","orcid":"https://orcid.org/0000-0003-1561-2467"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiming Lu","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18969","last_page":"18979"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.18000000715255737,"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":0.18000000715255737,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.13899999856948853,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.07490000128746033,"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/database-application","display_name":"Database application","score":0.32749998569488525},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.295199990272522},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.29350000619888306},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.26660001277923584},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.25459998846054077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6960999965667725},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.41429999470710754},{"id":"https://openalex.org/C2778625365","wikidata":"https://www.wikidata.org/wiki/Q5227393","display_name":"Database application","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29490000009536743},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2777999937534332},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1032","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1032","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1032.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.1032","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1032","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1032.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/G7036249533","display_name":null,"funder_award_id":"62376245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033985.pdf","grobid_xml":"https://content.openalex.org/works/W4416033985.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"text-to-SQL":[1],"systems":[2,21],"powered":[3],"by":[4],"large":[5],"language":[6,16,123],"models":[7],"(LLMs)":[8],"have":[9],"demonstrated":[10],"remarkable":[11],"performance":[12],"in":[13],"translating":[14],"natural":[15],"queries":[17],"into":[18],"SQL.However,":[19],"these":[20],"often":[22],"struggle":[23],"with":[24,64],"complex":[25,78],"database":[26,49,65,74,106,120],"structures":[27,121],"and":[28,39,70,88,91,112,122,129,145],"domain-specific":[29],"queries,":[30],"as":[31],"they":[32],"primarily":[33],"focus":[34],"on":[35,126,143,147,153],"enhancing":[36],"logical":[37],"reasoning":[38],"SQL":[40],"syntax":[41],"while":[42],"overlooking":[43],"the":[44,117,127,133],"critical":[45],"need":[46],"for":[47,98],"comprehensive":[48,105],"understanding.To":[50],"address":[51],"this":[52,96],"limitation,":[53],"we":[54],"propose":[55],"DB-Explore,":[56,136],"a":[57],"novel":[58],"framework":[59,103],"that":[60],"systematically":[61,84],"aligns":[62],"LLMs":[63],"knowledge":[66,97],"through":[67,108],"automated":[68,113],"exploration":[69],"instruction":[71,114],"synthesis.DB-Explore":[72],"constructs":[73],"graphs":[75],"to":[76,83,94],"capture":[77],"relational":[79],"schemas,":[80],"leverages":[81],"GPT-4":[82],"mine":[85],"structural":[86],"patterns":[87],"semantic":[89],"knowledge,":[90],"synthesizes":[92],"instructions":[93],"distill":[95],"efficient":[99],"fine-tuning":[100],"of":[101,135,141],"LLMs.Our":[102],"enables":[104],"understanding":[107],"diverse":[109],"sampling":[110],"strategies":[111],"generation,":[115],"bridging":[116],"gap":[118],"between":[119],"models.Experiments":[124],"conducted":[125],"SPIDER":[128],"BIRD":[130,144],"benchmarks":[131],"validate":[132],"effectiveness":[134],"achieving":[137],"an":[138],"execution":[139],"accuracy":[140],"67.0%":[142],"87.8%":[146],"SPIDER.Notably,":[148],"our":[149],"open-source":[150],"implementation":[151],"based":[152],"Qwen2.5-Coder-7Bachieves":[154],"state-of-the-art":[155],"results":[156],"at":[157],"minimal":[158],"computational":[159],"cost,":[160],"outperforming":[161],"several":[162],"GPT-4-driven":[163],"Text-to-SQL":[164],"systems.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-11-08T00:00:00"}