{"id":"https://openalex.org/W4414836602","doi":"https://doi.org/10.1145/3708359.3712083","title":"Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotation","display_name":"Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotation","publication_year":2025,"publication_date":"2025-03-19","ids":{"openalex":"https://openalex.org/W4414836602","doi":"https://doi.org/10.1145/3708359.3712083"},"language":"en","primary_location":{"id":"doi:10.1145/3708359.3712083","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708359.3712083","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3708359.3712083","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047416354","display_name":"Yuan Tian","orcid":"https://orcid.org/0000-0002-2200-5713"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuan Tian","raw_affiliation_strings":["Computer Science, Purdue university, West Lafayette, Indiana, USA,"],"raw_orcid":"https://orcid.org/0000-0002-2200-5713","affiliations":[{"raw_affiliation_string":"Computer Science, Purdue university, West Lafayette, Indiana, USA,","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Daniel Lee","orcid":"https://orcid.org/0009-0005-3061-1827"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Lee","raw_affiliation_strings":["Adobe Inc., San Jose, California, USA,"],"raw_orcid":"https://orcid.org/0009-0005-3061-1827","affiliations":[{"raw_affiliation_string":"Adobe Inc., San Jose, California, USA,","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fei Wu","orcid":"https://orcid.org/0000-0001-9083-0451"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Adobe Inc., Seattle, Washington, USA,"],"raw_orcid":"https://orcid.org/0000-0001-9083-0451","affiliations":[{"raw_affiliation_string":"Adobe Inc., Seattle, Washington, USA,","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007368820","display_name":"Tung Mai","orcid":"https://orcid.org/0009-0006-1081-5627"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tung Mai","raw_affiliation_strings":["Adobe Research, San Jose, California, USA,"],"raw_orcid":"https://orcid.org/0009-0006-1081-5627","affiliations":[{"raw_affiliation_string":"Adobe Research, San Jose, California, USA,","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kun Qian","orcid":"https://orcid.org/0000-0001-8868-0407"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Qian","raw_affiliation_strings":["Adobe Inc., Seattle, Washington, USA,"],"raw_orcid":"https://orcid.org/0000-0001-8868-0407","affiliations":[{"raw_affiliation_string":"Adobe Inc., Seattle, Washington, USA,","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119538797","display_name":"Siddhartha Sahai","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhartha Sahai","raw_affiliation_strings":["Adobe, Seattle, Washington, USA,"],"raw_orcid":"https://orcid.org/0009-0009-2167-2424","affiliations":[{"raw_affiliation_string":"Adobe, Seattle, Washington, USA,","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianyi Zhang","orcid":"https://orcid.org/0000-0002-5468-9347"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Zhang","raw_affiliation_strings":["Computer Science, Purdue University, West Lafayette, Indiana, USA,"],"raw_orcid":"https://orcid.org/0000-0002-5468-9347","affiliations":[{"raw_affiliation_string":"Computer Science, Purdue University, West Lafayette, Indiana, USA,","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yunyao Li","orcid":"https://orcid.org/0000-0001-8433-8719"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunyao Li","raw_affiliation_strings":["Adobe Inc., San Jose, California, USA,"],"raw_orcid":"https://orcid.org/0000-0001-8433-8719","affiliations":[{"raw_affiliation_string":"Adobe Inc., San Jose, California, USA,","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5047416354"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":8.693,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97493051,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1398","last_page":"1425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.967199981212616,"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":0.967199981212616,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.958299994468689,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9445000290870667,"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/annotation","display_name":"Annotation","score":0.6827999949455261},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.6434000134468079},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.45719999074935913},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.44119998812675476},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.42980000376701355},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41359999775886536},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3849000036716461},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.37959998846054077},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.3635999858379364}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8515999913215637},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6827999949455261},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.6434000134468079},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4205000102519989},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3433000147342682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34130001068115234},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32899999618530273},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3107999861240387},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C201932085","wikidata":"https://www.wikidata.org/wiki/Q642514","display_name":"Online analytical processing","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2777062904","wikidata":"https://www.wikidata.org/wiki/Q545406","display_name":"Toolchain","level":3,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3708359.3712083","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708359.3712083","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.15980","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.15980","pdf_url":"https://arxiv.org/pdf/2502.15980","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"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"}],"best_oa_location":{"id":"doi:10.1145/3708359.3712083","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708359.3712083","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2032374895","https://openalex.org/W2047705935","https://openalex.org/W2077302143","https://openalex.org/W2087189381","https://openalex.org/W2107130271","https://openalex.org/W2141373701","https://openalex.org/W2153710242","https://openalex.org/W2157289187","https://openalex.org/W2157749290","https://openalex.org/W2159934185","https://openalex.org/W2165382777","https://openalex.org/W2269738476","https://openalex.org/W2536574992","https://openalex.org/W2762513422","https://openalex.org/W2798663534","https://openalex.org/W2798753108","https://openalex.org/W2886983157","https://openalex.org/W2890431379","https://openalex.org/W2890585661","https://openalex.org/W2891691255","https://openalex.org/W2963216553","https://openalex.org/W2963477458","https://openalex.org/W2964271186","https://openalex.org/W2970172141","https://openalex.org/W2970442801","https://openalex.org/W2986532682","https://openalex.org/W3034835156","https://openalex.org/W3034999214","https://openalex.org/W3046744391","https://openalex.org/W3080132074","https://openalex.org/W3092609815","https://openalex.org/W3099700870","https://openalex.org/W3103962261","https://openalex.org/W3106221893","https://openalex.org/W3134547365","https://openalex.org/W3169001897","https://openalex.org/W3170014162","https://openalex.org/W3170978252","https://openalex.org/W3172767175","https://openalex.org/W3174699924","https://openalex.org/W3214600982","https://openalex.org/W4252076394","https://openalex.org/W4292198371","https://openalex.org/W4360991127","https://openalex.org/W4384662964","https://openalex.org/W4385572634","https://openalex.org/W4389520316","https://openalex.org/W4389523900","https://openalex.org/W4392348090","https://openalex.org/W4401042461"],"related_works":[],"abstract_inverted_index":{"Text-to-SQL":[0],"models,":[1],"which":[2],"parse":[3],"natural":[4],"language":[5],"(NL)":[6],"questions":[7],"to":[8,30,52,57,72],"executable":[9],"SQL":[10],"queries,":[11],"are":[12,148],"increasingly":[13],"adopted":[14],"in":[15,22,37,77,91,118],"real-world":[16,92],"applications.":[17,39],"However,":[18],"deploying":[19],"such":[20],"models":[21,45],"the":[23,31,58,70,109],"real":[24],"world":[25],"often":[26],"requires":[27],"adapting":[28],"them":[29],"highly":[32],"specialized":[33],"database":[34],"schemas":[35,87],"used":[36],"specific":[38],"We":[40],"find":[41],"that":[42,134,147],"existing":[43],"text-to-SQL":[44,83,103,113,138],"experience":[46],"significant":[47],"performance":[48,76],"drops":[49],"when":[50],"applied":[51],"new":[53,78],"schemas,":[54],"primarily":[55],"due":[56],"lack":[59],"of":[60,111],"domain-specific":[61],"data":[62,66,84,104,139],"for":[63,85],"fine-tuning.":[64],"This":[65],"scarcity":[67],"also":[68],"limits":[69],"ability":[71],"effectively":[73],"evaluate":[74],"model":[75],"domains.":[79],"Continuously":[80],"obtaining":[81],"high-quality":[82,112],"evolving":[86],"is":[88,156],"prohibitively":[89],"expensive":[90],"scenarios.":[93],"To":[94],"bridge":[95],"this":[96],"gap,":[97],"we":[98],"propose":[99],"SQLsynth,":[100],"a":[101,119],"human-in-the-loop":[102],"annotation":[105,130],"system.":[106],"SQLsynth":[107,127,135],"streamlines":[108],"creation":[110],"datasets":[114,146],"through":[115],"human-LLM":[116],"collaboration":[117],"structured":[120],"workflow.":[121],"A":[122],"within-subjects":[123],"user":[124],"study":[125],"comparing":[126],"with":[128],"manual":[129],"and":[131,144,152],"ChatGPT":[132],"shows":[133],"significantly":[136],"accelerates":[137],"annotation,":[140],"reduces":[141],"cognitive":[142],"load,":[143],"produces":[145],"more":[149],"accurate,":[150],"natural,":[151],"diverse.":[153],"Our":[154],"code":[155],"available":[157],"at":[158],"https://github.com/magic-YuanTian/SQLsynth.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}