{"id":"https://openalex.org/W4416251342","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227747","title":"End-to-End Text-to-SQL with Dataset Selection: Leveraging LLMs for Adaptive Query Generation","display_name":"End-to-End Text-to-SQL with Dataset Selection: Leveraging LLMs for Adaptive Query Generation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251342","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227747"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101814648","display_name":"Anurag Tripathi","orcid":"https://orcid.org/0000-0002-2289-2500"},"institutions":[{"id":"https://openalex.org/I1292842697","display_name":"Environmental Systems Research Institute (United States)","ror":"https://ror.org/0428exr50","country_code":"US","type":"company","lineage":["https://openalex.org/I1292842697"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anurag Tripathi","raw_affiliation_strings":["Infoorigin Pvt Ltd, Data Science"],"affiliations":[{"raw_affiliation_string":"Infoorigin Pvt Ltd, Data Science","institution_ids":["https://openalex.org/I1292842697"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120348805","display_name":"Vaibhav Patle","orcid":null},"institutions":[{"id":"https://openalex.org/I1292842697","display_name":"Environmental Systems Research Institute (United States)","ror":"https://ror.org/0428exr50","country_code":"US","type":"company","lineage":["https://openalex.org/I1292842697"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhav Patle","raw_affiliation_strings":["Infoorigin Pvt Ltd, Data Science"],"affiliations":[{"raw_affiliation_string":"Infoorigin Pvt Ltd, Data Science","institution_ids":["https://openalex.org/I1292842697"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046050883","display_name":"Abhinav Jain","orcid":"https://orcid.org/0000-0001-6017-5492"},"institutions":[{"id":"https://openalex.org/I1292842697","display_name":"Environmental Systems Research Institute (United States)","ror":"https://ror.org/0428exr50","country_code":"US","type":"company","lineage":["https://openalex.org/I1292842697"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Jain","raw_affiliation_strings":["Infoorigin Pvt Ltd, Data Science"],"affiliations":[{"raw_affiliation_string":"Infoorigin Pvt Ltd, Data Science","institution_ids":["https://openalex.org/I1292842697"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120348806","display_name":"Ayush Pundir","orcid":null},"institutions":[{"id":"https://openalex.org/I1292842697","display_name":"Environmental Systems Research Institute (United States)","ror":"https://ror.org/0428exr50","country_code":"US","type":"company","lineage":["https://openalex.org/I1292842697"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayush Pundir","raw_affiliation_strings":["Infoorigin Pvt Ltd, Data Science"],"affiliations":[{"raw_affiliation_string":"Infoorigin Pvt Ltd, Data Science","institution_ids":["https://openalex.org/I1292842697"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080898467","display_name":"Sasikumar Menon","orcid":"https://orcid.org/0000-0002-6514-8503"},"institutions":[{"id":"https://openalex.org/I4210155601","display_name":"Innovative Research (United States)","ror":"https://ror.org/04dec0k98","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sairam Menon","raw_affiliation_strings":["J&J Innovative Medicine Technology R&D,USA"],"affiliations":[{"raw_affiliation_string":"J&J Innovative Medicine Technology R&D,USA","institution_ids":["https://openalex.org/I4210155601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103338250","display_name":"Ajeet Kumar Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I1292842697","display_name":"Environmental Systems Research Institute (United States)","ror":"https://ror.org/0428exr50","country_code":"US","type":"company","lineage":["https://openalex.org/I1292842697"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ajeet Kumar Singh","raw_affiliation_strings":["Infoorigin Pvt Ltd, Data Science"],"affiliations":[{"raw_affiliation_string":"Infoorigin Pvt Ltd, Data Science","institution_ids":["https://openalex.org/I1292842697"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069548004","display_name":"Dorien Herremans","orcid":"https://orcid.org/0000-0001-8607-1640"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dorien Herremans","raw_affiliation_strings":["Singapore University of Technology and Design,Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design,Singapore","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101814648"],"corresponding_institution_ids":["https://openalex.org/I1292842697"],"apc_list":null,"apc_paid":null,"fwci":2.8331,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93088695,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6414999961853027,"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":0.6414999961853027,"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":0.1265999972820282,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.012600000016391277,"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":0.7703999876976013},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6478000283241272},{"id":"https://openalex.org/keywords/data-definition-language","display_name":"Data definition language","score":0.508899986743927},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5041000247001648},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.42879998683929443},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.383899986743927},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.36890000104904175},{"id":"https://openalex.org/keywords/stored-procedure","display_name":"Stored procedure","score":0.35830000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8920000195503235},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.7703999876976013},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6478000283241272},{"id":"https://openalex.org/C55596503","wikidata":"https://www.wikidata.org/wiki/Q1431648","display_name":"Data definition language","level":3,"score":0.508899986743927},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4620000123977661},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.42879998683929443},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4002000093460083},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.383899986743927},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36890000104904175},{"id":"https://openalex.org/C154420247","wikidata":"https://www.wikidata.org/wiki/Q846619","display_name":"Stored procedure","level":5,"score":0.35830000042915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35530000925064087},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C174252522","wikidata":"https://www.wikidata.org/wiki/Q3816772","display_name":"Natural language user interface","level":3,"score":0.350600004196167},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34150001406669617},{"id":"https://openalex.org/C54239708","wikidata":"https://www.wikidata.org/wiki/Q1329910","display_name":"View","level":3,"score":0.335999995470047},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C179531526","wikidata":"https://www.wikidata.org/wiki/Q595637","display_name":"Language Integrated Query","level":5,"score":0.3107999861240387},{"id":"https://openalex.org/C5968703","wikidata":"https://www.wikidata.org/wiki/Q267136","display_name":"Database model","level":3,"score":0.30059999227523804},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.29019999504089355},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.26919999718666077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2890431379","https://openalex.org/W2945102109","https://openalex.org/W2963993485","https://openalex.org/W3011387886","https://openalex.org/W3150263485","https://openalex.org/W3170656151","https://openalex.org/W3177130063","https://openalex.org/W3200079259","https://openalex.org/W3214600982","https://openalex.org/W4285227295","https://openalex.org/W4285244831","https://openalex.org/W4319862210","https://openalex.org/W4382202531","https://openalex.org/W4382202695","https://openalex.org/W4385571380","https://openalex.org/W4385573058","https://openalex.org/W4393065402","https://openalex.org/W4396571402","https://openalex.org/W4399879615","https://openalex.org/W4401666591","https://openalex.org/W4409362830"],"related_works":[],"abstract_inverted_index":{"Text-to-SQL":[0],"bridges":[1],"the":[2,59,75,96,121,142,150,153,159,176],"gap":[3],"between":[4],"natural":[5,116],"language":[6,45,117],"and":[7,108,152,185],"structured":[8],"database":[9,61,77,99,182],"language,":[10],"thus":[11],"allowing":[12],"nontechnical":[13],"users":[14],"to":[15,37,94,111,140,166],"easily":[16],"query":[17],"databases.":[18],"Traditional":[19],"approaches":[20],"model":[21],"text-to-SQL":[22,92],"as":[23],"a":[24,29,79,89,124,129,136],"direct":[25],"translation":[26,51],"task,":[27],"where":[28,73],"given":[30],"Natural":[31],"Language":[32],"Query":[33],"(NLQ)":[34],"is":[35,62],"mapped":[36],"an":[38],"SQL":[39,102,161,186],"command.":[40],"Recent":[41],"advances":[42],"in":[43,67,120,180],"large":[44,130],"models":[46,179],"(LLMs)":[47],"have":[48],"significantly":[49],"improved":[50],"accuracy,":[52],"however,":[53],"these":[54],"methods":[55],"all":[56],"require":[57],"that":[58,172],"target":[60],"pre-specified.":[63],"This":[64],"becomes":[65,78],"problematic":[66],"scenarios":[68],"with":[69],"multiple":[70],"extensive":[71],"databases,":[72],"identifying":[74],"correct":[76,143,167],"crucial":[80],"yet":[81],"overlooked":[82],"step.":[83],"In":[84],"this":[85],"paper,":[86],"we":[87,157],"propose":[88],"three-stage":[90],"end-to-end":[91],"framework":[93,174],"identify":[95],"user\u2019s":[97],"intended":[98],"before":[100],"generating":[101],"queries.":[103],"Our":[104],"approach":[105],"leverages":[106],"LLMs":[107],"prompt":[109],"engineering":[110],"extract":[112],"implicit":[113],"information":[114],"from":[115],"queries":[118],"(NLQs)":[119],"form":[122],"of":[123],"ruleset.":[125],"We":[126],"then":[127],"train":[128],"db_id":[131],"prediction":[132,184],"model,":[133],"which":[134],"includes":[135],"RoBERTa-based":[137],"finetuned":[138],"encoder,":[139],"predict":[141],"Database":[144],"identifier":[145],"(db_id)":[146],"based":[147],"on":[148],"both":[149,181],"NLQ":[151],"LLM-generated":[154],"rules.":[155],"Finally,":[156],"refine":[158],"generated":[160],"by":[162],"using":[163],"critic":[164],"agents":[165],"errors.":[168],"Experimental":[169],"results":[170],"demonstrate":[171],"our":[173],"outperforms":[175],"current":[177],"state-of-the-art":[178],"intent":[183],"generation":[187],"accuracy.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}