{"id":"https://openalex.org/W7163433859","doi":"https://doi.org/10.48550/arxiv.2606.03363","title":"EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge","display_name":"EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163433859","doi":"https://doi.org/10.48550/arxiv.2606.03363"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2606.03363","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.03363","pdf_url":"https://arxiv.org/pdf/2606.03363","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.03363","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134192575","display_name":"Chengxi Liao","orcid":"https://orcid.org/0009-0007-3092-4705","observed_orcids":["https://orcid.org/0009-0007-3092-4705"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liao, Chengxi","raw_affiliation_strings":["HKUST (GZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST (GZ)","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137779447","display_name":"Tao Xu","orcid":"https://orcid.org/0000-0003-3899-1500","observed_orcids":["https://orcid.org/0000-0003-3899-1500"]},"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":"Xu, Tao","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132837426","display_name":"Zulong Chen","orcid":null,"observed_orcids":[]},"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":"Chen, Zulong","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101155034","display_name":"Chuanfei Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405260597","display_name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen)","ror":"https://ror.org/040g1y854","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405260597"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Chuanfei","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)","institution_ids":["https://openalex.org/I4405260597"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137800604","display_name":"Yiyan Wang","orcid":null,"observed_orcids":[]},"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":"Wang, Yiyan","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137784001","display_name":"Xinyun Wang","orcid":null,"observed_orcids":[]},"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":"Wang, Xinyun","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137743834","display_name":"Yanlong Zhang","orcid":null,"observed_orcids":[]},"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":"Zhang, Yanlong","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136625898","display_name":"Xiaojun Chen","orcid":"https://orcid.org/0000-0002-2818-4652","observed_orcids":["https://orcid.org/0000-0002-2818-4652"]},"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":"Chen, Xiaojun","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137782313","display_name":"Zhibo Yang","orcid":null,"observed_orcids":[]},"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":"Yang, Zhibo","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013127195","display_name":"Zeyi Wen","orcid":"https://orcid.org/0000-0003-3370-6053","observed_orcids":["https://orcid.org/0000-0003-3370-6053"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen, Zeyi","raw_affiliation_strings":["HKUST (GZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST (GZ)","institution_ids":["https://openalex.org/I4405261251"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/T10028","display_name":"Topic Modeling","score":0.46700000762939453,"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":0.46700000762939453,"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":0.2101999968290329,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.1096000000834465,"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/text-to-sql","display_name":"text-to-SQL","score":0.8759999871253967},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.6570000052452087},{"id":"https://openalex.org/keywords/enterprise-knowledge","display_name":"enterprise knowledge","score":0.9409999847412109},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6940000057220459},{"id":"https://openalex.org/keywords/business-domain","display_name":"business domain","score":0.367000013589859}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7182999849319458},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6019999980926514},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5889999866485596},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.43950000405311584},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.43160000443458557},{"id":"https://openalex.org/C11066294","wikidata":"https://www.wikidata.org/wiki/Q1518244","display_name":"Business rule","level":4,"score":0.4049000144004822},{"id":"https://openalex.org/C27295321","wikidata":"https://www.wikidata.org/wiki/Q831795","display_name":"Enterprise information system","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C185765463","wikidata":"https://www.wikidata.org/wiki/Q1318054","display_name":"Enterprise software","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C193669473","wikidata":"https://www.wikidata.org/wiki/Q5001867","display_name":"Business domain","level":5,"score":0.3953999876976013},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C53996427","wikidata":"https://www.wikidata.org/wiki/Q5380387","display_name":"Enterprise integration","level":3,"score":0.34630000591278076},{"id":"https://openalex.org/C10590034","wikidata":"https://www.wikidata.org/wiki/Q1048431","display_name":"Enterprise architecture","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C138824270","wikidata":"https://www.wikidata.org/wiki/Q3318162","display_name":"Enterprise modelling","level":4,"score":0.3278000056743622},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.320499986410141},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2962999939918518},{"id":"https://openalex.org/C146342590","wikidata":"https://www.wikidata.org/wiki/Q11606385","display_name":"Enterprise systems engineering","level":4,"score":0.29440000653266907},{"id":"https://openalex.org/C67571701","wikidata":"https://www.wikidata.org/wiki/Q1318054","display_name":"Enterprise system","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2644999921321869}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2606.03363","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.03363","pdf_url":"https://arxiv.org/pdf/2606.03363","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2606.03363","doi":"https://doi.org/10.48550/arxiv.2606.03363","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03363","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.03363","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.03363","pdf_url":"https://arxiv.org/pdf/2606.03363","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7163433859.pdf","grobid_xml":"https://content.openalex.org/works/W7163433859.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2751448157","https://openalex.org/W2768409085","https://openalex.org/W4317940064","https://openalex.org/W4384615768","https://openalex.org/W4396571402","https://openalex.org/W4399115971","https://openalex.org/W4404344612","https://openalex.org/W4404406411","https://openalex.org/W4414682143","https://openalex.org/W7130402983"],"related_works":["https://openalex.org/W4402955398","https://openalex.org/W7133239790","https://openalex.org/W7212968308","https://openalex.org/W7082324591","https://openalex.org/W7204089756","https://openalex.org/W7204921959","https://openalex.org/W7084129136","https://openalex.org/W7130689383","https://openalex.org/W7128574233","https://openalex.org/W7125809978"],"abstract_inverted_index":{"Text-to-SQL":[0,58],"enables":[1],"natural":[2],"language":[3],"access":[4],"to":[5],"databases,":[6,27],"and":[7,21,28,50,88,90],"recent":[8],"LLMs":[9],"have":[10],"substantially":[11],"advanced":[12],"its":[13],"capabilities.":[14],"Existing":[15],"benchmarks":[16],"such":[17,44],"as":[18,45],"Spider,":[19],"BIRD,":[20],"Spider~2.0":[22],"evaluate":[23],"schema":[24,89],"generalization,":[25],"large-scale":[26],"realistic":[29],"workflows,":[30],"but":[31],"largely":[32],"overlook":[33],"enterprise":[34,118],"scenarios":[35],"where":[36],"SQL":[37,93,115],"generation":[38,116],"depends":[39],"on":[40],"private":[41],"business":[42,66,77],"knowledge,":[43],"internal":[46],"metrics,":[47],"reporting":[48],"conventions,":[49],"organizational":[51],"rules.":[52],"We":[53],"introduce":[54],"EntSQL,":[55],"an":[56],"enterprise-oriented":[57],"benchmark":[59],"for":[60],"evaluating":[61],"long-context":[62],"grounding":[63,114],"over":[64],"proprietary":[65],"documents.":[67],"EntSQL":[68],"contains":[69],"1,066":[70],"aligned":[71],"Chinese-English":[72],"semantic":[73],"examples":[74,81],"across":[75],"five":[76],"domains,":[78],"with":[79],"most":[80],"requiring":[82],"domain":[83],"knowledge":[84],"beyond":[85],"the":[86,98,111],"question":[87],"involving":[91],"complex":[92],"structures.":[94],"On":[95],"English":[96],"inputs,":[97],"best":[99],"evaluated":[100],"system":[101],"reaches":[102],"only":[103],"15.9\\%":[104],"when":[105],"long-form":[106],"documents":[107],"are":[108],"provided,":[109],"highlighting":[110],"difficulty":[112],"of":[113],"in":[117],"knowledge.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-06-04T00:00:00"}