{"id":"https://openalex.org/W7164053223","doi":"https://doi.org/10.48550/arxiv.2606.08245","title":"ZAS-SQL: Distilling Rules from Failures for Zero-Shot Text-to-SQL","display_name":"ZAS-SQL: Distilling Rules from Failures for Zero-Shot Text-to-SQL","publication_year":2026,"publication_date":"2026-06-06","ids":{"openalex":"https://openalex.org/W7164053223","doi":"https://doi.org/10.48550/arxiv.2606.08245"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08245","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08245","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.08245","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138270708","display_name":"Hongzhou Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Hongzhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109654330","display_name":"Yixin Gou","orcid":"https://orcid.org/0009-0004-1051-0976"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gou, Yixin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138265371","display_name":"Wenjia Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wenjia","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":0.17870000004768372,"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":0.17870000004768372,"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/T11719","display_name":"Data Quality and Management","score":0.16689999401569366,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.1200999990105629,"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/executable","display_name":"Executable","score":0.49559998512268066},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4478999972343445},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.4219000041484833},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4124999940395355},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.40549999475479126},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.38370001316070557},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3619000017642975},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.3296000063419342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.765999972820282},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.49559998512268066},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3824000060558319},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37959998846054077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37860000133514404},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34200000762939453},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3296000063419342},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C107094494","wikidata":"https://www.wikidata.org/wiki/Q428453","display_name":"Fault tree analysis","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C3746660","wikidata":"https://www.wikidata.org/wiki/Q1068763","display_name":"Rule of inference","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08245","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08245","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.08245","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08245","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"score":0.7244707942008972,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"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":[0,55,73],"translates":[1],"natural":[2],"language":[3,15],"into":[4],"executable":[5],"SQL":[6],"queries.":[7],"Few-shot":[8],"in-context":[9],"learning":[10],"methods":[11,156],"built":[12,157],"upon":[13,158],"large":[14],"models":[16],"(LLMs)":[17],"achieve":[18],"strong":[19,194],"performance,":[20],"yet":[21],"their":[22],"reliance":[23],"on":[24,65,138],"demonstrations":[25],"limits":[26],"cross-domain":[27],"generalization":[28],"and":[29,89,117,134,141,150,154],"consumes":[30],"substantial":[31],"context":[32],"window":[33],"space.":[34],"Existing":[35],"zero-shot":[36,54,72,148,187],"methods,":[37],"lacking":[38],"effective":[39],"generation":[40,78,91],"constraints,":[41],"still":[42],"fall":[43],"short":[44],"of":[45,189],"few-shot":[46,153],"approaches.":[47],"We":[48],"observe":[49],"that":[50,75,113,169],"LLM":[51],"failures":[52],"in":[53,104],"are":[56],"not":[57],"random":[58],"but":[59],"exhibit":[60],"systematic,":[61],"recurring":[62],"patterns.":[63],"Building":[64],"this":[66],"observation,":[67],"we":[68],"propose":[69],"a":[70,84,108,146,181],"fully":[71],"framework":[74,112,129,185],"distills":[76],"core":[77],"rules":[79],"from":[80],"failure":[81],"cases":[82],"through":[83],"Map-Reduce-based":[85],"rule":[86,171],"distillation":[87,172],"pipeline":[88],"improves":[90],"quality":[92],"via":[93],"three":[94],"complementary":[95],"modules:":[96],"knowledge-augmented":[97],"schema":[98],"representation,":[99],"which":[100,121],"supplements":[101],"missing":[102],"semantics":[103],"Data":[105],"Definition":[106],"Language;":[107],"rule-driven":[109],"structured":[110],"reasoning":[111],"suppresses":[114],"structural":[115],"deviations;":[116],"Execution-Guided":[118],"Early":[119],"Stopping,":[120],"enables":[122],"low-cost":[123],"self-correction.":[124],"On":[125,160],"Spider,":[126],"the":[127,139,161,170,184],"proposed":[128],"achieves":[130,166],"up":[131],"to":[132],"87.2%":[133],"88.6%":[135],"execution":[136],"accuracy":[137],"Dev":[140],"Test":[142],"sets,":[143],"respectively,":[144],"establishing":[145],"new":[147],"state-of-the-art":[149],"surpassing":[151],"multiple":[152],"fine-tuning":[155],"GPT-4/4o.":[159],"domain-specific":[162],"dataset":[163],"UrbanPlan,":[164],"it":[165],"81.3%,":[167],"confirming":[168],"approach":[173],"generalizes":[174],"across":[175],"domains.":[176],"Moreover,":[177],"when":[178],"equipped":[179],"with":[180],"4B-parameter":[182],"model,":[183],"surpasses":[186],"baselines":[188],"leading":[190],"closed-source":[191],"models,":[192],"demonstrating":[193],"model":[195],"generality.":[196]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}