{"id":"https://openalex.org/W7134954916","doi":"https://doi.org/10.1109/icdmw69685.2025.00343","title":"Enhancing LLM Fine-Tuning for Text-to-SQLs by SQL Quality Measurement","display_name":"Enhancing LLM Fine-Tuning for Text-to-SQLs by SQL Quality Measurement","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7134954916","doi":"https://doi.org/10.1109/icdmw69685.2025.00343"},"language":null,"primary_location":{"id":"doi:10.1109/icdmw69685.2025.00343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","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/A5007353421","display_name":"Shouvon Sarker","orcid":null},"institutions":[{"id":"https://openalex.org/I250520410","display_name":"Prairie View A&M University","ror":"https://ror.org/0449kf092","country_code":"US","type":"education","lineage":["https://openalex.org/I250520410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shouvon Sarker","raw_affiliation_strings":["Prairie View A&M University,CREDIT Center and Department of Electrical and Computer Engineering,Prairie View,TX,USA,77446"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prairie View A&M University,CREDIT Center and Department of Electrical and Computer Engineering,Prairie View,TX,USA,77446","institution_ids":["https://openalex.org/I250520410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006284276","display_name":"Xishuang Dong","orcid":"https://orcid.org/0000-0002-3742-0071"},"institutions":[{"id":"https://openalex.org/I250520410","display_name":"Prairie View A&M University","ror":"https://ror.org/0449kf092","country_code":"US","type":"education","lineage":["https://openalex.org/I250520410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xishuang Dong","raw_affiliation_strings":["Prairie View A&M University,CREDIT Center and Department of Electrical and Computer Engineering,Prairie View,TX,USA,77446"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prairie View A&M University,CREDIT Center and Department of Electrical and Computer Engineering,Prairie View,TX,USA,77446","institution_ids":["https://openalex.org/I250520410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063982441","display_name":"Xiangfang Li","orcid":"https://orcid.org/0000-0003-0334-4733"},"institutions":[{"id":"https://openalex.org/I250520410","display_name":"Prairie View A&M University","ror":"https://ror.org/0449kf092","country_code":"US","type":"education","lineage":["https://openalex.org/I250520410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangfang Li","raw_affiliation_strings":["Prairie View A&M University,CREDIT Center and Department of Electrical and Computer Engineering,Prairie View,TX,USA,77446"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prairie View A&M University,CREDIT Center and Department of Electrical and Computer Engineering,Prairie View,TX,USA,77446","institution_ids":["https://openalex.org/I250520410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082506620","display_name":"Lijun Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I250520410","display_name":"Prairie View A&M University","ror":"https://ror.org/0449kf092","country_code":"US","type":"education","lineage":["https://openalex.org/I250520410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lijun Qian","raw_affiliation_strings":["Prairie View A&M University,CREDIT Center and Department of Electrical and Computer Engineering,Prairie View,TX,USA,77446"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prairie View A&M University,CREDIT Center and Department of Electrical and Computer Engineering,Prairie View,TX,USA,77446","institution_ids":["https://openalex.org/I250520410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I250520410"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54836534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2673","last_page":"2678"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13820","display_name":"SAS software applications and methods","score":0.25920000672340393,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13820","display_name":"SAS software applications and methods","score":0.25920000672340393,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.2410999983549118,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.05779999867081642,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/quality","display_name":"Quality (philosophy)","score":0.47699999809265137},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.44519999623298645},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.3513999879360199},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.28949999809265137},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.28850001096725464},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.2847999930381775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6007000207901001},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38769999146461487},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2994999885559082},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2847999930381775},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2565999925136566},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdmw69685.2025.00343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4538482392","display_name":null,"funder_award_id":"80NSSC22KM0052","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W3103801878","https://openalex.org/W3150263485","https://openalex.org/W4285244831","https://openalex.org/W4382202695","https://openalex.org/W4385573058","https://openalex.org/W4389519829","https://openalex.org/W4396571402","https://openalex.org/W4399175046","https://openalex.org/W4404782579","https://openalex.org/W7133205963","https://openalex.org/W7133224126"],"related_works":[],"abstract_inverted_index":{"Text-to-SQLs":[0,43,75,137],"enables":[1,100],"non-expert":[2],"users":[3],"to":[4,49,56,72,84,151],"effortlessly":[5],"retrieve":[6],"desired":[7],"information":[8],"from":[9],"relational":[10],"databases":[11],"using":[12],"natural":[13],"language":[14],"queries.":[15],"While":[16],"recent":[17],"advancements,":[18],"particularly":[19],"with":[20],"Large":[21],"Language":[22],"Models":[23],"(LLMs)":[24],"like":[25,53,154],"GPT":[26],"and":[27,93,103,113,130,148,156],"T5,":[28],"have":[29],"shown":[30],"impressive":[31],"performance":[32,144],"on":[33,109,122],"large-scale":[34],"benchmarks":[35],"such":[36],"as":[37],"BIRD,":[38],"current":[39],"state-of-the-art":[40],"(SOTA)":[41],"LLM-based":[42],"models":[44,153],"often":[45],"require":[46],"significant":[47],"efforts":[48],"develop":[50],"auxiliary":[51],"tools":[52],"SQL":[54,69,80,88],"classifiers":[55],"achieve":[57],"high":[58],"performance.":[59,76],"This":[60,97],"paper":[61],"proposed":[62,117],"a":[63,79],"novel":[64],"approach":[65],"that":[66],"only":[67],"needs":[68],"Quality":[70],"Measurement":[71],"enhance":[73],"LLMs-based":[74],"It":[77],"establishes":[78],"quality":[81],"evaluation":[82],"mechanism":[83],"assess":[85],"the":[86,123],"generated":[87],"queries":[89],"against":[90],"predefined":[91],"criteria":[92],"actual":[94],"database":[95],"responses.":[96],"feedback":[98],"loop":[99],"continuous":[101],"learning":[102],"refinement":[104],"of":[105],"model":[106],"outputs":[107],"based":[108],"both":[110,146],"syntactic":[111],"correctness":[112],"semantic":[114],"accuracy.":[115],"The":[116],"method":[118],"undergoes":[119],"comprehensive":[120],"validation":[121],"BIRD":[124],"benchmark,":[125],"assessing":[126],"Execution":[127],"Accuracy":[128],"(EX)":[129],"Valid":[131],"Efficiency":[132],"Score":[133],"(VES)":[134],"across":[135],"various":[136],"difficulty":[138],"levels.":[139],"Experimental":[140],"results":[141],"reveal":[142],"competitive":[143],"in":[145],"EX":[147],"VES":[149],"compared":[150],"SOTA":[152],"GPT4":[155],"T5.":[157]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-03-12T00:00:00"}