{"id":"https://openalex.org/W7108322724","doi":"https://doi.org/10.1145/3767695.3769489","title":"Retrieval-Augmented NL2SQL Generation with Data-Centric Query Capsules for Enterprise Applications","display_name":"Retrieval-Augmented NL2SQL Generation with Data-Centric Query Capsules for Enterprise Applications","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7108322724","doi":"https://doi.org/10.1145/3767695.3769489"},"language":null,"primary_location":{"id":"doi:10.1145/3767695.3769489","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769489","pdf_url":null,"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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767695.3769489","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jisoo Jang","orcid":"https://orcid.org/0009-0008-4449-2381"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jisoo Jang","raw_affiliation_strings":["Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wen-Syan Li","orcid":"https://orcid.org/0009-0007-0496-3479"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wen-Syan Li","raw_affiliation_strings":["Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61537318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.4641000032424927,"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":0.4641000032424927,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.08399999886751175,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.06909999996423721,"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/sql","display_name":"SQL","score":0.656000018119812},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5841000080108643},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.5698000192642212},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5224999785423279},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.5198000073432922},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.4925999939441681},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44999998807907104},{"id":"https://openalex.org/keywords/rdf-query-language","display_name":"RDF query language","score":0.4212000072002411},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.40130001306533813},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3935000002384186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8586000204086304},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.656000018119812},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5841000080108643},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.5698000192642212},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5224999785423279},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.5198000073432922},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.4925999939441681},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C96956885","wikidata":"https://www.wikidata.org/wiki/Q6138701","display_name":"RDF query language","level":5,"score":0.4212000072002411},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3953000009059906},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C174252522","wikidata":"https://www.wikidata.org/wiki/Q3816772","display_name":"Natural language user interface","level":3,"score":0.38839998841285706},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3783000111579895},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C179531526","wikidata":"https://www.wikidata.org/wiki/Q595637","display_name":"Language Integrated Query","level":5,"score":0.3628000020980835},{"id":"https://openalex.org/C32977378","wikidata":"https://www.wikidata.org/wiki/Q604737","display_name":"Data control language","level":5,"score":0.3456000089645386},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C172722865","wikidata":"https://www.wikidata.org/wiki/Q2302053","display_name":"Spatial query","level":5,"score":0.32429999113082886},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.32359999418258667},{"id":"https://openalex.org/C2779729312","wikidata":"https://www.wikidata.org/wiki/Q784232","display_name":"Query plan","level":5,"score":0.31220000982284546},{"id":"https://openalex.org/C148230440","wikidata":"https://www.wikidata.org/wiki/Q1172264","display_name":"Datalog","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C55596503","wikidata":"https://www.wikidata.org/wiki/Q1431648","display_name":"Data definition language","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2935999929904938},{"id":"https://openalex.org/C145644426","wikidata":"https://www.wikidata.org/wiki/Q169411","display_name":"Unified Modeling Language","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27810001373291016},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C133264317","wikidata":"https://www.wikidata.org/wiki/Q1397689","display_name":"Object Constraint Language","level":5,"score":0.2597000002861023},{"id":"https://openalex.org/C54239708","wikidata":"https://www.wikidata.org/wiki/Q1329910","display_name":"View","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3767695.3769489","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769489","pdf_url":null,"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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3767695.3769489","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769489","pdf_url":null,"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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.40077224373817444,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2028509346","https://openalex.org/W2084413241","https://openalex.org/W2145618437","https://openalex.org/W4385571778","https://openalex.org/W4400909566"],"related_works":[],"abstract_inverted_index":{"Using":[0],"natural":[1,83],"language":[2,84],"to":[3],"query":[4,81,92],"databases":[5],"has":[6],"become":[7],"increasingly":[8],"popular":[9],"for":[10,25,188],"making":[11],"data":[12],"access":[13],"more":[14],"intuitive.":[15],"While":[16],"Large":[17],"Language":[18],"Models":[19],"(LLMs)":[20],"offer":[21],"a":[22,47,71,75,80,89,107,153],"scalable":[23],"approach":[24,187],"Natural":[26],"Language-to-SQL":[27],"(NL2SQL)":[28],"translation,":[29],"they":[30],"often":[31],"struggle":[32],"with":[33,59,94],"unfamiliar":[34],"schemas":[35],"and":[36,113,128,142,144,149,182],"domain-specific":[37],"logic":[38],"in":[39,116],"enterprise":[40,190],"environments.":[41],"In":[42],"this":[43],"work,":[44],"we":[45,104],"present":[46],"data-centric,":[48],"retrieval-augmented":[49],"inference":[50],"framework":[51],"that":[52,78,110,132,162],"improves":[53,137],"SQL":[54,87,90,117],"generation":[55,118],"by":[56,140,147,168],"supplying":[57],"LLMs":[58],"curated":[60],"examples":[61],"drawn":[62],"from":[63],"prior":[64],"workloads.":[65],"We":[66],"introduce":[67],"the":[68,99,126,133,158,177,183],"concept":[69],"of":[70,86,101,135,171,180,185],"Query":[72],"Capsule":[73],"(QC),":[74],"structured":[76],"unit":[77],"encapsulates":[79],"context\u2014a":[82],"description":[85],"intent\u2014and":[88],"template\u2014a":[91],"skeleton":[93],"typed":[95],"placeholders.":[96],"To":[97],"evaluate":[98],"benefit":[100],"providing":[102],"QCs,":[103],"propose":[105],"Merit,":[106],"novel":[108],"metric":[109],"captures":[111],"structural":[112],"semantic":[114],"improvements":[115],"when":[119],"QCs":[120,136,181],"are":[121],"included.":[122],"Our":[123],"experiments":[124],"on":[125,157],"Spider":[127],"BIRD":[129],"benchmarks":[130],"demonstrate":[131],"inclusion":[134],"execution":[138,166],"accuracy":[139,167],"4.58%":[141],"5.79%,":[143],"Merit":[145],"score":[146],"5.67%":[148],"8.24%,":[150],"respectively.":[151],"Furthermore,":[152],"real-world":[154],"case":[155],"study":[156],"TPC-H":[159],"benchmark":[160],"shows":[161],"QC-based":[163],"retrieval":[164],"enhances":[165],"an":[169],"average":[170],"2.63":[172],"times.":[173],"These":[174],"findings":[175],"validate":[176],"practical":[178],"usefulness":[179],"importance":[184],"data-centric":[186],"robust":[189],"NL2SQL":[191],"systems.":[192]},"counts_by_year":[],"updated_date":"2025-12-04T23:47:47.292601","created_date":"2025-12-03T00:00:00"}