{"id":"https://openalex.org/W7109064377","doi":"https://doi.org/10.1145/3769813","title":"PLForge: Enhancing Language Models for Natural Language to Procedural Extensions of SQL","display_name":"PLForge: Enhancing Language Models for Natural Language to Procedural Extensions of SQL","publication_year":2025,"publication_date":"2025-12-04","ids":{"openalex":"https://openalex.org/W7109064377","doi":"https://doi.org/10.1145/3769813"},"language":"en","primary_location":{"id":"doi:10.1145/3769813","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769813","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769813","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3769813","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hang Zhang","orcid":"https://orcid.org/0009-0009-5918-3183"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-5918-3183","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chaokun Wang","orcid":"https://orcid.org/0000-0002-2986-2574"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaokun Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2986-2574","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongwei Li","orcid":"https://orcid.org/0009-0008-8813-2433"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-8813-2433","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cheng Wu","orcid":"https://orcid.org/0009-0002-4481-405X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Wu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-4481-405X","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Songyao Wang","orcid":"https://orcid.org/0009-0001-4054-9853"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songyao Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-4054-9853","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yabin Liu","orcid":"https://orcid.org/0009-0007-2808-5279"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabin Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-2808-5279","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gengyuan Shi","orcid":"https://orcid.org/0009-0007-2938-1539"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gengyuan Shi","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-2938-1539","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ziyang Liu","orcid":"https://orcid.org/0009-0007-4238-1533"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-4238-1533","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51961919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"6","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.2361000031232834,"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":0.2361000031232834,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.14390000700950623,"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":0.14270000159740448,"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":0.6255999803543091},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5658000111579895},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.48420000076293945},{"id":"https://openalex.org/keywords/data-manipulation-language","display_name":"Data manipulation language","score":0.48330000042915344},{"id":"https://openalex.org/keywords/data-definition-language","display_name":"Data definition language","score":0.47690001130104065},{"id":"https://openalex.org/keywords/natural-language-user-interface","display_name":"Natural language user interface","score":0.46779999136924744},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.44519999623298645},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.3871000111103058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8658999800682068},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6255999803543091},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5658000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48739999532699585},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.48330000042915344},{"id":"https://openalex.org/C55596503","wikidata":"https://www.wikidata.org/wiki/Q1431648","display_name":"Data definition language","level":3,"score":0.47690001130104065},{"id":"https://openalex.org/C174252522","wikidata":"https://www.wikidata.org/wiki/Q3816772","display_name":"Natural language user interface","level":3,"score":0.46779999136924744},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4580000042915344},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C67463725","wikidata":"https://www.wikidata.org/wiki/Q17081452","display_name":"Natural language programming","level":5,"score":0.37950000166893005},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35850000381469727},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C146206909","wikidata":"https://www.wikidata.org/wiki/Q531152","display_name":"Declarative programming","level":4,"score":0.34139999747276306},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C160713754","wikidata":"https://www.wikidata.org/wiki/Q1389965","display_name":"Maintainability","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30000001192092896},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2827000021934509},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2754000127315521},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.27160000801086426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769813","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769813","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769813","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3769813","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769813","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769813","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4248116613","display_name":null,"funder_award_id":"No. 62372264 and No. 92467203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4929059444","display_name":null,"funder_award_id":"62372264","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5947250162","display_name":null,"funder_award_id":"92467203","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7109064377.pdf","grobid_xml":"https://content.openalex.org/works/W7109064377.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1970709149","https://openalex.org/W2101000001","https://openalex.org/W2269738476","https://openalex.org/W2536574992","https://openalex.org/W3164278511","https://openalex.org/W4366660081","https://openalex.org/W4396571402","https://openalex.org/W4402043038","https://openalex.org/W4407385475"],"related_works":[],"abstract_inverted_index":{"Procedural":[0],"Language":[1],"extensions":[2,105],"of":[3,25,44,51,59,106,124,131,146,167,183,199],"SQL":[4,87,100],"(abbr.":[5],"PL/SQL)":[6],"enhance":[7,141],"database":[8,30],"programming":[9],"by":[10],"integrating":[11],"procedural":[12,104],"constructs":[13],"with":[14,128],"SQL's":[15],"declarative":[16],"syntax,":[17],"thereby":[18],"improving":[19],"the":[20,41,48,56,92,103,113,142,165,181,220,223],"reusability,":[21],"modularity,":[22],"and":[23,134,155,203,211,236],"maintainability":[24],"SQL.":[26],"Besides,":[27],"PL/SQL":[28,65,71,143],"in":[29,35,75,81,232],"systems":[31],"presents":[32],"significant":[33],"challenges":[34],"real-world":[36],"development,":[37],"primarily":[38],"due":[39],"to":[40,64,162],"inherent":[42],"complexity":[43],"programming.":[45],"To":[46,140],"reduce":[47],"development":[49],"difficulty":[50],"PL/SQL,":[52],"this":[53,117],"paper":[54],"studies":[55],"novel":[57],"task":[58],"translating":[60,82],"natural":[61,83],"language":[62,76,84,126],"(NL)":[63],"(i.e.,":[66,89],"NL-to-PL/SQL),":[67],"aimed":[68],"at":[69],"simplifying":[70],"development.":[72],"Recent":[73],"advancements":[74],"models":[77,127,231],"have":[78],"shown":[79],"promise":[80],"questions":[85],"into":[86],"queries":[88],"Text-to-SQL).":[90],"However,":[91],"state-of-the-art":[93],"Text-to-SQL":[94],"methods":[95],"focus":[96],"only":[97],"on":[98,201,208],"single":[99],"queries,":[101],"neglecting":[102],"SQL,":[107],"which":[108],"limits":[109],"their":[110],"effectiveness":[111],"for":[112,137,178,191,219],"NL-to-PL/SQL":[114,138,184,193,221],"task.":[115],"In":[116],"paper,":[118],"we":[119,148,169,186],"propose":[120,170],"PLForge,":[121,147,168],"a":[122,150,171,188,197],"suite":[123],"pre-trained":[125],"parameter":[129],"configurations":[130],"3B,":[132],"7B,":[133],"15B,":[135],"tailored":[136,176],"tasks.":[139],"generation":[144],"capabilities":[145],"leverage":[149],"curated":[151],"PL/SQL-centric":[152],"data":[153],"corpus":[154],"employ":[156],"an":[157],"incremental":[158],"pre-training":[159],"approach.":[160],"Furthermore,":[161],"fully":[163],"exploit":[164],"potential":[166],"comprehensive":[172],"prompt":[173],"construction":[174],"strategy":[175],"specifically":[177,218],"PL/SQL.":[179],"Given":[180],"scarcity":[182],"datasets,":[185],"develop":[187],"template-based":[189],"method":[190],"generating":[192],"data.":[194],"We":[195],"conduct":[196],"series":[198],"experiments":[200],"PLForge":[202,228],"several":[204],"baseline":[205],"models.":[206],"Based":[207],"execution":[209],"match":[210,213],"exact":[212],"metrics":[214],"that":[215,227],"are":[216],"designed":[217],"task,":[222],"experimental":[224],"results":[225],"demonstrate":[226],"outperforms":[229],"existing":[230],"both":[233],"in-context":[234],"learning":[235],"supervised":[237],"fine-tuning":[238],"settings.":[239]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-12-06T00:00:00"}
