{"id":"https://openalex.org/W7167888502","doi":"https://doi.org/10.48550/arxiv.2607.08161","title":"SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillation","display_name":"SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillation","publication_year":2026,"publication_date":"2026-07-09","ids":{"openalex":"https://openalex.org/W7167888502","doi":"https://doi.org/10.48550/arxiv.2607.08161"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.08161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.08161","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.08161","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140430405","display_name":"Wangyu Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Wangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100542390","display_name":"Xiaojian Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Xiaojian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140400383","display_name":"Rong Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Rong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085760057","display_name":"Zaiyang Yu","orcid":"https://orcid.org/0000-0002-3425-1153"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Zaiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140393099","display_name":"Xuhang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xuhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132645546","display_name":"W K Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Wenjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140446726","display_name":"Zhenhong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhenhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.49619999527931213,"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":0.49619999527931213,"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":0.09309999644756317,"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/T14347","display_name":"Big Data and Digital Economy","score":0.08299999684095383,"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/task","display_name":"Task (project management)","score":0.6855000257492065},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5971999764442444},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5583000183105469},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5116999745368958},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5008000135421753},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.45019999146461487},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4124999940395355},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4122999906539917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918999791145325},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6855000257492065},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5971999764442444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5587000250816345},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5583000183105469},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5116999745368958},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5008000135421753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4993000030517578},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.40470001101493835},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3222000002861023},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3156999945640564},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.08161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.08161","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.08161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.08161","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-SQL":[0,69,179],"is":[1,96],"a":[2,52,113],"fundamental":[3],"task":[4,70],"in":[5,38,128,181],"natural":[6,18],"language":[7,22,58],"processing":[8],"that":[9,55,137],"enables":[10],"users":[11],"to":[12,61],"interact":[13],"with":[14,166],"structured":[15,94],"databases":[16],"using":[17],"language.":[19],"While":[20],"large":[21],"models":[23,59],"(LLMs)":[24],"have":[25],"demonstrated":[26],"remarkable":[27],"performance":[28,64,127,151],"on":[29,67,112,132,145],"this":[30,42],"task,":[31],"their":[32],"substantial":[33],"computational":[34],"requirements":[35],"hinder":[36],"deployment":[37],"resource-constrained":[39],"settings.":[40],"In":[41],"paper,":[43],"we":[44],"introduce":[45],"SQuaD-SQL":[46,138],"(Small-Qualified":[47],"and":[48,78,117,158,175],"Distilled":[49],"for":[50,178],"SQL),":[51],"novel":[53],"approach":[54,62],"empowers":[56],"small":[57],"(SLMs)":[60],"the":[63,68,133,146,150],"of":[65,143,152],"LLMs":[66,99,153],"while":[71,154],"significantly":[72],"improving":[73],"efficiency":[74],"through":[75],"knowledge":[76,95],"distillation":[77],"synthetic":[79,90,123],"data":[80,91,124],"generation.":[81],"Our":[82],"method":[83],"comprises":[84],"three":[85],"key":[86],"components:":[87],"(1)":[88],"LLM-based":[89],"generation,":[92],"where":[93,121],"extracted":[97],"from":[98],"via":[100],"carefully":[101],"designed":[102],"prompting":[103],"strategies;":[104],"(2)":[105],"parameter-efficient":[106],"fine-tuning,":[107,120],"enabling":[108],"full":[109],"model":[110],"training":[111,168],"single":[114],"consumer-grade":[115],"GPU;":[116],"(3)":[118],"domain-adaptive":[119],"domain-specific":[122],"further":[125],"enhances":[126],"targeted":[129],"domains.":[130],"Experiments":[131],"WikiSQL":[134],"dataset":[135],"demonstrate":[136],"achieves":[139],"an":[140],"execution":[141],"accuracy":[142],"86.9%":[144],"test":[147],"set,":[148],"approaching":[149],"offering":[155],"faster":[156],"inference":[157],"lower":[159],"memory":[160],"usage.":[161],"These":[162],"results":[163],"suggest":[164],"that,":[165],"proper":[167],"strategies,":[169],"SLMs":[170],"can":[171],"serve":[172],"as":[173],"practical":[174],"efficient":[176],"alternatives":[177],"applications":[180],"resource-limited":[182],"environments.":[183]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-11T00:00:00"}