{"id":"https://openalex.org/W4399175046","doi":"https://doi.org/10.1145/3654930","title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","display_name":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","publication_year":2024,"publication_date":"2024-05-29","ids":{"openalex":"https://openalex.org/W4399175046","doi":"https://doi.org/10.1145/3654930"},"language":"en","primary_location":{"id":"doi:10.1145/3654930","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3654930","pdf_url":null,"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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069391613","display_name":"Haoyang Li","orcid":"https://orcid.org/0000-0002-6610-3841"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyang Li","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6610-3841","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101681014","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0003-2019-225X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2019-225X","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057511308","display_name":"Hanbing Liu","orcid":"https://orcid.org/0009-0000-4582-3340"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanbing Liu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-4582-3340","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739546","display_name":"Ju Fan","orcid":"https://orcid.org/0000-0003-4729-9903"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju Fan","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4729-9903","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412329","display_name":"Xiaokang Zhang","orcid":"https://orcid.org/0009-0009-3855-3093"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Zhang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-3855-3093","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102732126","display_name":"Jun Zhu","orcid":"https://orcid.org/0009-0006-1127-3057"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Zhu","raw_affiliation_strings":["BEIJING AI-FINANCE TECHNOLOGIES CO. LTD, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-1127-3057","affiliations":[{"raw_affiliation_string":"BEIJING AI-FINANCE TECHNOLOGIES CO. LTD, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103266906","display_name":"Renjie Wei","orcid":"https://orcid.org/0009-0007-5786-1513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renjie Wei","raw_affiliation_strings":["BEIJING AI-FINANCE TECHNOLOGIES CO. LTD, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-5786-1513","affiliations":[{"raw_affiliation_string":"BEIJING AI-FINANCE TECHNOLOGIES CO. LTD, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056341653","display_name":"Hongyan Pan","orcid":"https://orcid.org/0009-0008-8367-1518"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyan Pan","raw_affiliation_strings":["BEIJING AI-FINANCE TECHNOLOGIES CO. LTD, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-8367-1518","affiliations":[{"raw_affiliation_string":"BEIJING AI-FINANCE TECHNOLOGIES CO. LTD, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619237","display_name":"Cuiping Li","orcid":"https://orcid.org/0000-0003-0089-1045"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cuiping Li","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0089-1045","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100420391","display_name":"Hong Chen","orcid":"https://orcid.org/0000-0001-8132-9382"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Chen","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8132-9382","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":24.9896,"has_fulltext":false,"cited_by_count":102,"citation_normalized_percentile":{"value":0.99717615,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"2","issue":"3","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9994000196456909,"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/T10260","display_name":"Software Engineering Research","score":0.9330000281333923,"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/computer-science","display_name":"Computer science","score":0.8614531755447388},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.7723135948181152},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5200064778327942},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.459838330745697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4461784362792969},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4218788146972656},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4216890335083008},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.41600197553634644},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4020245671272278},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3503037691116333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8614531755447388},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.7723135948181152},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5200064778327942},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.459838330745697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4461784362792969},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4218788146972656},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4216890335083008},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.41600197553634644},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4020245671272278},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3503037691116333},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3654930","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3654930","pdf_url":null,"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":null,"license_id":null,"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":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4055083048","display_name":null,"funder_award_id":"62322214, U23A20299, 62076245, 62072460, 62172424, 62276270","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G6880998225","display_name":null,"funder_award_id":"62122090, 62072461","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/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1932742904","https://openalex.org/W2022322548","https://openalex.org/W2269738476","https://openalex.org/W2762513422","https://openalex.org/W2788306232","https://openalex.org/W2890431379","https://openalex.org/W2891691255","https://openalex.org/W2945102109","https://openalex.org/W2952205826","https://openalex.org/W2963617989","https://openalex.org/W2964271186","https://openalex.org/W2964315653","https://openalex.org/W2971323043","https://openalex.org/W2981852735","https://openalex.org/W3034999214","https://openalex.org/W3035140194","https://openalex.org/W3035231859","https://openalex.org/W3093819145","https://openalex.org/W3098281910","https://openalex.org/W3102020135","https://openalex.org/W3103611182","https://openalex.org/W3122241445","https://openalex.org/W3129831491","https://openalex.org/W3134503905","https://openalex.org/W3156636935","https://openalex.org/W3156729426","https://openalex.org/W3170014162","https://openalex.org/W3170721718","https://openalex.org/W3173274550","https://openalex.org/W3175488485","https://openalex.org/W3175818566","https://openalex.org/W3199077625","https://openalex.org/W3214600982","https://openalex.org/W4288089799","https://openalex.org/W4313131742","https://openalex.org/W4366660081","https://openalex.org/W4381326864","https://openalex.org/W4382202695","https://openalex.org/W4385570984","https://openalex.org/W4385572634","https://openalex.org/W4385573504","https://openalex.org/W4389520779","https://openalex.org/W4391709246","https://openalex.org/W6600018615","https://openalex.org/W6600050674","https://openalex.org/W6600195515","https://openalex.org/W6600424091","https://openalex.org/W6600449182","https://openalex.org/W6600538214","https://openalex.org/W6601289607","https://openalex.org/W6601899773","https://openalex.org/W6602754419","https://openalex.org/W6603548105","https://openalex.org/W6603713569","https://openalex.org/W6605656274","https://openalex.org/W6608408508","https://openalex.org/W6699065970","https://openalex.org/W6743235451","https://openalex.org/W6910691047"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Language":[0],"models":[1,32,67],"have":[2,41],"shown":[3],"promising":[4],"performance":[5],"on":[6,26,127,154,202],"the":[7,21,42,57,78,100,108,131,158,163],"task":[8],"of":[9,20,44,64,112,133],"translating":[10],"natural":[11],"language":[12,31,66,86],"questions":[13],"into":[14],"SQL":[15,109],"queries":[16],"(Text-to-SQL).":[17],"However,":[18],"most":[19],"state-of-the-art":[22],"(SOTA)":[23],"approaches":[24],"rely":[25],"powerful":[27],"yet":[28],"closed-source":[29],"large":[30],"(LLMs),":[33],"such":[34,170],"as":[35,171,177,179],"ChatGPT":[36],"and":[37,51,136,144,175,186,200],"GPT-4,":[38],"which":[39,88],"may":[40],"limitations":[43],"unclear":[45],"model":[46],"architectures,":[47],"data":[48,147],"privacy":[49],"risks,":[50],"expensive":[52],"inference":[53],"overheads.":[54],"To":[55,106],"address":[56,130],"limitations,":[58],"we":[59,114,129],"introduce":[60],"CodeS,":[61,113],"a":[62,83,121,145],"series":[63],"pre-trained":[65],"with":[68,92],"parameters":[69],"ranging":[70],"from":[71],"1B":[72],"to":[73],"15B,":[74],"specifically":[75,122],"designed":[76],"for":[77,184],"text-to-SQL":[79,206],"task.":[80],"CodeS":[81,195],"is":[82],"fully":[84],"open-source":[85],"model,":[87],"achieves":[89,196],"superior":[90],"accuracy":[91,199],"much":[93],"smaller":[94],"parameter":[95],"sizes.":[96],"This":[97],"paper":[98],"studies":[99],"research":[101],"challenges":[102,132],"in":[103],"building":[104],"CodeS.":[105],"enhance":[107],"generation":[110],"abilities":[111],"adopt":[115],"an":[116],"incremental":[117],"pre-training":[118],"approach":[119],"using":[120],"curated":[123],"SQL-centric":[124],"corpus.":[125],"Based":[126],"this,":[128],"schema":[134],"linking":[135],"rapid":[137],"domain":[138],"adaptation":[139],"through":[140],"strategic":[141],"prompt":[142],"construction":[143],"bi-directional":[146],"augmentation":[148],"technique.":[149],"We":[150],"conduct":[151],"comprehensive":[152],"evaluations":[153],"multiple":[155],"datasets,":[156],"including":[157],"widely":[159],"used":[160],"Spider":[161],"benchmark,":[162,167],"newly":[164],"released":[165],"BIRD":[166],"robustness-diagnostic":[168],"benchmarks":[169],"Spider-DK,":[172],"Spider-Syn,":[173],"Spider-Realistic,":[174],"Dr.Spider,":[176],"well":[178],"two":[180],"real-world":[181],"datasets":[182],"created":[183],"financial":[185],"academic":[187],"applications.":[188],"The":[189],"experimental":[190],"results":[191],"show":[192],"that":[193],"our":[194],"new":[197],"SOTA":[198],"robustness":[201],"nearly":[203],"all":[204],"challenging":[205],"benchmarks.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":33},{"year":2025,"cited_by_count":61},{"year":2024,"cited_by_count":8}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}