{"id":"https://openalex.org/W7204921959","doi":"https://doi.org/10.18653/2026.findings-emnlp.593","title":"BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations","display_name":"BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204921959","doi":"https://doi.org/10.18653/2026.findings-emnlp.593"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.593","doi":"https://doi.org/10.18653/2026.findings-emnlp.593","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.593","pdf_url":"https://aclanthology.org/2026.findings-emnlp.593.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-emnlp.593.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103207718","display_name":"Yunfan Zhou","orcid":"https://orcid.org/0009-0009-7814-4390","observed_orcids":["https://orcid.org/0009-0009-7814-4390"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfan Zhou","raw_affiliation_strings":["State Key Lab of CAD&CG , Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&CG , Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137705067","display_name":"Qiming Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiming Shi","raw_affiliation_strings":["State Key Lab of CAD&CG , Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&CG , Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148918083","display_name":"Yizhou Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Yang","raw_affiliation_strings":["School of Software Technology , Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Technology , Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088199295","display_name":"Di Weng","orcid":"https://orcid.org/0000-0003-2712-7274","observed_orcids":["https://orcid.org/0000-0003-2712-7274"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Weng","raw_affiliation_strings":["School of Software Technology , Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Technology , Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115817152","display_name":"Yingcai Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingcai Wu","raw_affiliation_strings":["State Key Lab of CAD&CG , Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&CG , Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6970044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12511","last_page":"12533"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.35010001063346863,"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":0.35010001063346863,"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":0.19900000095367432,"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":0.16609999537467957,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/text-to-sql","display_name":"text-to-SQL","score":0.9829999804496765},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.4269999861717224},{"id":"https://openalex.org/keywords/external-knowledge-retrieval","display_name":"external knowledge retrieval","score":0.8230000138282776},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6840000152587891},{"id":"https://openalex.org/keywords/few-shot-learning","display_name":"few-shot learning","score":0.6420000195503235},{"id":"https://openalex.org/keywords/database-question-answering","display_name":"database question answering","score":0.4050000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8865000009536743},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6912000179290771},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.5626000165939331},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5379999876022339},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.38920000195503235},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3379000127315521},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3368000090122223},{"id":"https://openalex.org/C174252522","wikidata":"https://www.wikidata.org/wiki/Q3816772","display_name":"Natural language user interface","level":3,"score":0.32690000534057617},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C179531526","wikidata":"https://www.wikidata.org/wiki/Q595637","display_name":"Language Integrated Query","level":5,"score":0.29100000858306885},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C55596503","wikidata":"https://www.wikidata.org/wiki/Q1431648","display_name":"Data definition language","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.593","doi":"https://doi.org/10.18653/2026.findings-emnlp.593","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.593","pdf_url":"https://aclanthology.org/2026.findings-emnlp.593.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.29345","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.29345","pdf_url":"https://arxiv.org/pdf/2608.29345","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.2608.29345","doi":"https://doi.org/10.48550/arxiv.2608.29345","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.29345","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":"doi:10.18653/2026.findings-emnlp.593","doi":"https://doi.org/10.18653/2026.findings-emnlp.593","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.593","pdf_url":"https://aclanthology.org/2026.findings-emnlp.593.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204921959.pdf","grobid_xml":"https://content.openalex.org/works/W7204921959.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4403836156","https://openalex.org/W7133239790","https://openalex.org/W7140089314","https://openalex.org/W7130335360","https://openalex.org/W7212968308","https://openalex.org/W4378505284","https://openalex.org/W7163433859","https://openalex.org/W4402670079","https://openalex.org/W4412944569","https://openalex.org/W7128785721"],"abstract_inverted_index":{"While":[0],"recent":[1],"Large":[2],"Language":[3],"Model":[4],"(LLM)based":[5],"text-to-SQL":[6,87,155],"systems":[7],"achieve":[8],"impressive":[9],"performance":[10],"on":[11,21],"standard":[12],"benchmarks,":[13],"they":[14],"struggle":[15],"when":[16],"user":[17],"queries":[18,109],"implicitly":[19],"rely":[20],"domain-specific":[22],"knowledge,":[23,57],"such":[24,56],"as":[25],"business":[26],"logic,":[27],"data":[28],"conventions,":[29],"and":[30,113,126],"analytical":[31],"practices,":[32],"that":[33,134],"is":[34,101],"neither":[35],"captured":[36],"by":[37],"the":[38,44,158],"schema":[39],"nor":[40],"explicitly":[41],"stated":[42],"in":[43],"natural":[45,93],"language":[46,94],"question.Historical":[47],"SQL":[48,98,115],"query":[49,163],"logs":[50,164],"offer":[51],"a":[52,75,131],"valuable":[53],"source":[54],"of":[55,66,78,122,160],"yet":[58],"existing":[59,143],"benchmarks":[60],"do":[61],"not":[62],"adequately":[63],"support":[64],"evaluation":[65,121],"history-driven":[67],"approaches.To":[68],"address":[69],"this":[70],"gap,":[71],"we":[72],"introduce":[73,130],"BIRD-History,":[74],"benchmark":[76],"consisting":[77],"1,393":[79],"tasks":[80],"across":[81,153],"11":[82],"databases,":[83],"designed":[84],"to":[85,90],"evaluate":[86],"systems'":[88],"ability":[89],"ground":[91],"underspecified":[92,167],"questions":[95],"using":[96],"historical":[97,108,139,162],"scripts.Each":[99],"task":[100],"annotated":[102],"with":[103],"ground-truth":[104],"labels":[105],"specifying":[106],"which":[107,114],"contain":[110],"relevant":[111,136],"knowledge":[112,127,137],"clauses":[116],"encode":[117],"it,":[118],"enabling":[119],"systematic":[120],"both":[123],"retrieval":[124],"effectiveness":[125],"utilization.We":[128],"further":[129],"plug-in":[132],"retriever":[133],"extracts":[135],"from":[138],"logs,":[140],"seamlessly":[141],"enhancing":[142],"few-shot":[144],"textto-SQL":[145],"pipelines":[146],"without":[147],"architectural":[148],"modifications.Experiments":[149],"demonstrate":[150],"consistent":[151],"improvements":[152],"four":[154],"systems,":[156],"highlighting":[157],"value":[159],"leveraging":[161],"for":[165],"handling":[166],"queries.":[168]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-09-02T00:00:00"}