{"id":"https://openalex.org/W4415348225","doi":"https://doi.org/10.1109/tkde.2026.3657851","title":"XiYan-SQL: A Novel Multi-Generator Framework for Text-to-SQL","display_name":"XiYan-SQL: A Novel Multi-Generator Framework for Text-to-SQL","publication_year":2026,"publication_date":"2026-01-27","ids":{"openalex":"https://openalex.org/W4415348225","doi":"https://doi.org/10.1109/tkde.2026.3657851"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2026.3657851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2026.3657851","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.04701","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yifu Liu","orcid":"https://orcid.org/0009-0002-2090-7059"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifu Liu","raw_affiliation_strings":["Alibaba Cloud Computing Company, Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-2090-7059","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing Company, Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343741","display_name":"Yin Zhu","orcid":"https://orcid.org/0009-0002-1063-515X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Zhu","raw_affiliation_strings":["Alibaba Cloud Computing Company, Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-1063-515X","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing Company, Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020118426","display_name":"Yingqi Gao","orcid":"https://orcid.org/0000-0002-3247-0272"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingqi Gao","raw_affiliation_strings":["Alibaba Cloud Computing Company, Ltd., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing Company, Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020904548","display_name":"Zhiling Luo","orcid":"https://orcid.org/0000-0002-0540-7307"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiling Luo","raw_affiliation_strings":["Alibaba Cloud Computing Company, Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0540-7307","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing Company, Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348753","display_name":"Xiaoxia Li","orcid":"https://orcid.org/0000-0002-3510-2942"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxia Li","raw_affiliation_strings":["Alibaba Cloud Computing Company, Ltd., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing Company, Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaorong Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorong Shi","raw_affiliation_strings":["Alibaba Cloud Computing Company, Ltd., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing Company, Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101834055","display_name":"Y\u00fa H\u00f3n\u0261","orcid":"https://orcid.org/0000-0003-0738-5620"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuntao Hong","raw_affiliation_strings":["Alibaba Cloud Computing Company, Ltd., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing Company, Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101403129","display_name":"Jinyang Gao","orcid":"https://orcid.org/0000-0002-2094-3554"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyang Gao","raw_affiliation_strings":["Alibaba Cloud Computing Company, Ltd., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing Company, Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022118078","display_name":"Haijun Yu","orcid":"https://orcid.org/0000-0002-3398-0880"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Li","raw_affiliation_strings":["Alibaba Cloud Computing Company, Ltd., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing Company, Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040297543","display_name":"Bolin Ding","orcid":"https://orcid.org/0000-0003-1535-9692"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bolin Ding","raw_affiliation_strings":["Alibaba Cloud Computing Company, Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1535-9692","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing Company, Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057864403","display_name":"Jingren Zhou","orcid":"https://orcid.org/0000-0002-4220-2634"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingren Zhou","raw_affiliation_strings":["Alibaba Cloud Computing Company, Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4220-2634","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing Company, Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":36.9221,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.99512984,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"38","issue":"4","first_page":"2474","last_page":"2487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.5062000155448914,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.5062000155448914,"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/sql","display_name":"SQL","score":0.7145000100135803},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4765999913215637},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.476500004529953},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3977999985218048},{"id":"https://openalex.org/keywords/pl/sql","display_name":"PL/SQL","score":0.3944000005722046},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.38609999418258667},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.36570000648498535},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.3434000015258789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7915999889373779},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.7145000100135803},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.476500004529953},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4652000069618225},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C32145003","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"PL/SQL","level":5,"score":0.3944000005722046},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C103000020","wikidata":"https://www.wikidata.org/wiki/Q1978426","display_name":"Nested set model","level":3,"score":0.33889999985694885},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33730000257492065},{"id":"https://openalex.org/C179531526","wikidata":"https://www.wikidata.org/wiki/Q595637","display_name":"Language Integrated Query","level":5,"score":0.33649998903274536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31200000643730164},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C154420247","wikidata":"https://www.wikidata.org/wiki/Q846619","display_name":"Stored procedure","level":5,"score":0.25429999828338623},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C167544706","wikidata":"https://www.wikidata.org/wiki/Q360842","display_name":"SQL/PSM","level":5,"score":0.2524000108242035}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tkde.2026.3657851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2026.3657851","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2507.04701","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.04701","pdf_url":"https://arxiv.org/pdf/2507.04701","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.04701","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.04701","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":"pmh:oai:arXiv.org:2507.04701","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.04701","pdf_url":"https://arxiv.org/pdf/2507.04701","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W4402042542","https://openalex.org/W4399175046","https://openalex.org/W4404782579","https://openalex.org/W2890431379","https://openalex.org/W4385245566","https://openalex.org/W2896457183","https://openalex.org/W3035231859","https://openalex.org/W4396571402","https://openalex.org/W7133205963","https://openalex.org/W4402671560","https://openalex.org/W4402683779","https://openalex.org/W4411403530","https://openalex.org/W4382202531","https://openalex.org/W4408564229","https://openalex.org/W2162006472","https://openalex.org/W4412623423","https://openalex.org/W3141797743","https://openalex.org/W4402670291","https://openalex.org/W4412876971","https://openalex.org/W4391876619"],"related_works":[],"abstract_inverted_index":{"To":[0],"leverage":[1],"the":[2,10,66,72,83,90,119,136,150],"advantages":[3],"of":[4,28,85,123,133,157],"LLM":[5],"in":[6,9],"addressing":[7],"challenges":[8],"Text-to-SQL":[11],"task,":[12],"we":[13,75],"present":[14],"XiYan-SQL,":[15],"an":[16,155],"innovative":[17],"framework":[18],"effectively":[19],"generating":[20,47],"and":[21,37,50,95,97,115,121],"utilizing":[22],"multiple":[23,39,48,99],"SQL":[24,52,68,86,94,110],"candidates.":[25],"It":[26,144],"consists":[27],"three":[29],"components:":[30],"1)":[31],"a":[32,43,55,59,77,129],"Schema":[33],"Filter":[34],"module":[35],"filtering":[36],"obtaining":[38],"relevant":[40],"schemas;":[41],"2)":[42],"multi-generator":[44,73],"ensemble":[45],"approach":[46],"high-quality":[49],"diverse":[51],"queries;":[53],"3)":[54],"selection":[56],"model":[57],"with":[58,102,154],"candidate":[60],"reorganization":[61],"strategy":[62,80],"implemented":[63],"to":[64,81],"obtain":[65],"optimal":[67],"query.":[69],"Specifically,":[70],"for":[71,89],"ensemble,":[74],"employ":[76],"multi-task":[78],"fine-tuning":[79,107],"enhance":[82],"capabilities":[84],"generation":[87,100,104],"models":[88,101],"intrinsic":[91],"alignment":[92],"between":[93],"text,":[96],"construct":[98],"distinct":[103],"styles":[105],"by":[106],"across":[108],"different":[109],"formats.":[111],"The":[112],"experimental":[113],"results":[114],"comprehensive":[116],"analysis":[117],"demonstrate":[118],"effectiveness":[120],"robustness":[122],"our":[124],"framework.":[125],"Overall,":[126],"XiYan-SQL":[127],"achieves":[128],"new":[130],"SOTA":[131,147],"performance":[132,148],"75.63%":[134],"on":[135,149],"notable":[137],"BIRD":[138],"benchmark,":[139],"surpassing":[140],"all":[141],"previous":[142],"methods.":[143],"also":[145],"attains":[146],"Spider":[151],"test":[152],"set":[153],"accuracy":[156],"89.65%.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-20T00:00:00"}
