{"id":"https://openalex.org/W4417070755","doi":"https://doi.org/10.48550/arxiv.2509.08575","title":"SQLGovernor: An LLM-powered SQL Toolkit for Real World Application","display_name":"SQLGovernor: An LLM-powered SQL Toolkit for Real World Application","publication_year":2025,"publication_date":"2025-09-10","ids":{"openalex":"https://openalex.org/W4417070755","doi":"https://doi.org/10.48550/arxiv.2509.08575"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.08575","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.08575","pdf_url":"https://arxiv.org/pdf/2509.08575","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.08575","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101944040","display_name":"Jie Jiang","orcid":"https://orcid.org/0000-0001-7019-2077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035174613","display_name":"Siqi Shen","orcid":"https://orcid.org/0000-0001-7479-0189"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Siqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113862159","display_name":"Haining Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Haining","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079524660","display_name":"Yang Li","orcid":"https://orcid.org/0000-0001-5706-1830"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052400920","display_name":"Yu Shen","orcid":"https://orcid.org/0000-0002-5145-5182"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007093788","display_name":"Danqing Huang","orcid":"https://orcid.org/0000-0002-3112-0617"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Danqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103108332","display_name":"Bo Qian","orcid":"https://orcid.org/0000-0001-7571-9237"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063073383","display_name":"Yinjun Wu","orcid":"https://orcid.org/0000-0002-9770-5765"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yinjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008772211","display_name":"Wentao Zhang","orcid":"https://orcid.org/0000-0002-7532-5550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wentao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082951250","display_name":"Bin Cui","orcid":"https://orcid.org/0000-0002-8489-0084"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5045876611","display_name":"Peng Chen","orcid":"https://orcid.org/0000-0001-8223-8458"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Peng","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.5516999959945679,"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":0.5516999959945679,"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/T11719","display_name":"Data Quality and Management","score":0.04809999838471413,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.04490000009536743,"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/sql","display_name":"SQL","score":0.7529000043869019},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.6270999908447266},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6080999970436096},{"id":"https://openalex.org/keywords/online-analytical-processing","display_name":"Online analytical processing","score":0.560699999332428},{"id":"https://openalex.org/keywords/rewriting","display_name":"Rewriting","score":0.4814000129699707},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.4690000116825104},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.4327000081539154},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3950999975204468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8664000034332275},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.7529000043869019},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6507999897003174},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.6270999908447266},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6080999970436096},{"id":"https://openalex.org/C201932085","wikidata":"https://www.wikidata.org/wiki/Q642514","display_name":"Online analytical processing","level":3,"score":0.560699999332428},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.4814000129699707},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.4690000116825104},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.42910000681877136},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C154420247","wikidata":"https://www.wikidata.org/wiki/Q846619","display_name":"Stored procedure","level":5,"score":0.39089998602867126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3431999981403351},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.3416000008583069},{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C55596503","wikidata":"https://www.wikidata.org/wiki/Q1431648","display_name":"Data definition language","level":3,"score":0.3400999903678894},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C2779729312","wikidata":"https://www.wikidata.org/wiki/Q784232","display_name":"Query plan","level":5,"score":0.3384000062942505},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.32519999146461487},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.29589998722076416},{"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/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2653000056743622},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C117667704","wikidata":"https://www.wikidata.org/wiki/Q2011708","display_name":"Object Query Language","level":5,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.08575","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.08575","pdf_url":"https://arxiv.org/pdf/2509.08575","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.2509.08575","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.08575","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.08575","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.08575","pdf_url":"https://arxiv.org/pdf/2509.08575","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"SQL":[0,38],"queries":[1],"in":[2,24,146],"real":[3],"world":[4],"analytical":[5],"environments,":[6,148],"whether":[7],"written":[8],"by":[9,59,95,135],"humans":[10],"or":[11,20],"generated":[12],"automatically":[13],"often":[14],"suffer":[15],"from":[16],"syntax":[17,45],"errors,":[18],"inefficiency,":[19],"semantic":[21],"misalignment,":[22],"especially":[23],"complex":[25],"OLAP":[26],"scenarios.":[27],"To":[28],"address":[29],"these":[30],"challenges,":[31],"we":[32],"propose":[33],"SQLGovernor,":[34],"an":[35],"LLM":[36],"powered":[37],"toolkit":[39],"that":[40,126],"unifies":[41],"multiple":[42],"functionalities,":[43],"including":[44],"correction,":[46,77],"query":[47,49],"rewriting,":[48],"modification,":[50],"and":[51,74,108,117,154],"consistency":[52],"verification":[53],"within":[54],"a":[55,64,89],"structured":[56],"framework":[57],"enhanced":[58],"knowledge":[60],"management.":[61],"SQLGovernor":[62,127,149],"introduces":[63],"fragment":[65],"wise":[66],"processing":[67],"strategy":[68],"to":[69,101,137],"enable":[70],"fine":[71],"grained":[72],"rewriting":[73],"localized":[75],"error":[76],"significantly":[78],"reducing":[79],"the":[80,84,99,130],"cognitive":[81],"load":[82],"on":[83,112,142],"LLM.":[85],"It":[86],"further":[87],"incorporates":[88],"hybrid":[90],"self":[91],"learning":[92],"mechanism":[93],"guided":[94],"expert":[96],"feedback,":[97],"allowing":[98],"system":[100],"continuously":[102],"improve":[103],"through":[104],"DBMS":[105],"output":[106],"analysis":[107],"rule":[109],"validation.":[110],"Experiments":[111],"benchmarks":[113],"such":[114],"as":[115,120,122],"BIRD":[116,118],"CRITIC,":[119],"well":[121],"industrial":[123],"datasets,":[124],"show":[125],"consistently":[128],"boosts":[129],"performance":[131],"of":[132],"base":[133],"models":[134],"up":[136],"10%,":[138],"while":[139],"minimizing":[140],"reliance":[141],"manual":[143],"expertise.":[144],"Deployed":[145],"production":[147],"demonstrates":[150],"strong":[151],"practical":[152],"utility":[153],"effective":[155],"performance.":[156]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}