{"id":"https://openalex.org/W7082324591","doi":null,"title":"Injection of Domain-Specific Knowledge for Enterprise Text-to-SQL","display_name":"Injection of Domain-Specific Knowledge for Enterprise Text-to-SQL","publication_year":2025,"publication_date":"2025-05-01","ids":{"openalex":"https://openalex.org/W7082324591"},"language":"en","primary_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/162742","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/162742","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/162742/1/choi-jchoi-meng-eecs-2025-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.mit.edu/bitstream/1721.1/162742/1/choi-jchoi-meng-eecs-2025-thesis.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Choi, Justin J.","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Choi, Justin J.","raw_affiliation_strings":["Computer Science and Engineering , MIT , 2025","MASTER OF ENGINEERING IN ELECTRICAL ENGINEERING AND COMPUTER SCIENCE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering , MIT , 2025","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"MASTER OF ENGINEERING IN ELECTRICAL ENGINEERING AND COMPUTER SCIENCE","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7333999872207642,"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":0.7333999872207642,"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":0.09359999746084213,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0551999993622303,"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/text-to-sql","display_name":"text-to-SQL","score":0.8889999985694885},{"id":"https://openalex.org/keywords/business-databases","display_name":"business databases","score":0.8309999704360962},{"id":"https://openalex.org/keywords/knowledge-injection","display_name":"knowledge injection","score":0.9350000023841858},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"domain knowledge","score":0.8960000276565552},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8299999833106995},{"id":"https://openalex.org/keywords/retrieval-augmentation","display_name":"retrieval augmentation","score":0.8519999980926514},{"id":"https://openalex.org/keywords/hybrid-search","display_name":"hybrid retrieval","score":0.5540000200271606},{"id":"https://openalex.org/keywords/table-retrieval","display_name":"table retrieval","score":0.8309999704360962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6923999786376953},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6204000115394592},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5788999795913696},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.5489000082015991},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.48260000348091125},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C136227091","wikidata":"https://www.wikidata.org/wiki/Q5380376","display_name":"Enterprise data management","level":3,"score":0.42829999327659607},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37049999833106995},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3398999869823456},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C27295321","wikidata":"https://www.wikidata.org/wiki/Q831795","display_name":"Enterprise information system","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:dspace.mit.edu:1721.1/162742","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/162742","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/162742/1/choi-jchoi-meng-eecs-2025-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/162742","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/162742","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/162742/1/choi-jchoi-meng-eecs-2025-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7082324591.pdf","grobid_xml":"https://content.openalex.org/works/W7082324591.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W3027879771","https://openalex.org/W4285134344","https://openalex.org/W4309046837","https://openalex.org/W4309217888","https://openalex.org/W4312046042","https://openalex.org/W4388639106","https://openalex.org/W4389523875","https://openalex.org/W4391833713","https://openalex.org/W4395022004","https://openalex.org/W4398794928","https://openalex.org/W4402955398","https://openalex.org/W4403487197","https://openalex.org/W4403883262","https://openalex.org/W4404406411","https://openalex.org/W4404783077","https://openalex.org/W4407356147","https://openalex.org/W4408039286","https://openalex.org/W4411119602","https://openalex.org/W4411120274","https://openalex.org/W4415185633","https://openalex.org/W4415796409","https://openalex.org/W7133239790"],"related_works":["https://openalex.org/W4403487197","https://openalex.org/W4400480762","https://openalex.org/W4401202692","https://openalex.org/W4417426834","https://openalex.org/W7163433859","https://openalex.org/W4402955398","https://openalex.org/W4396571402","https://openalex.org/W4412623829","https://openalex.org/W7130335360","https://openalex.org/W7128574233"],"abstract_inverted_index":{"This":[0,43],"work":[1,51],"examines":[2,45],"the":[3,31,46,62,73,101,157,160,164,169,199],"current":[4],"state":[5],"of":[6,35,64,76,86,92,103,112,159,166,201],"using":[7,58,190],"large":[8],"language":[9],"models":[10,147],"(LLMs)":[11],"to":[12,50,60,123,145,211],"solve":[13],"Text-to-SQL":[14,67,153,194],"tasks":[15],"on":[16,23,66,78,168,187],"databases":[17],"in":[18,38,207,213],"an":[19,192],"enterprise":[20,41,53,79,227],"setting.":[21,42],"Benchmarks":[22],"publicly":[24],"available":[25],"datasets":[26],"do":[27],"not":[28],"fully":[29],"capture":[30],"difficulty":[32],"and":[33,106,138,204],"complexity":[34],"this":[36],"task":[37,172],"a":[39,83,90,131],"real-world,":[40],"study":[44],"critical":[47],"steps":[48],"needed":[49],"with":[52,142,148,176],"data":[54],"as":[55,57,116,217,219],"well":[56,218],"knowledge-injection":[59,161,183,203],"enhance":[61],"performance":[63,75,165],"LLMs":[65,77,167,209],"tasks.":[68],"We":[69,129,155,180],"begin":[70],"by":[71,162],"evaluating":[72],"baseline":[74],"databases,":[80],"revealing":[81],"that":[82,135,182,223],"predominant":[84],"source":[85],"failure":[87,221],"stems":[88],"from":[89],"lack":[91],"domain-specific":[93,202],"knowledge.":[94,108,179],"To":[95],"improve":[96],"performance,":[97],"we":[98],"explore":[99],"knowledge-injection:":[100],"process":[102],"incorporating":[104],"internal":[105],"external":[107,120,150,178],"Internal":[109],"knowledge":[110,121,151],"consists":[111],"database-specific":[113],"information":[114],"such":[115],"join":[117],"logic,":[118],"while":[119],"refers":[122],"institutional":[124],"acronyms":[125],"or":[126],"group":[127],"names.":[128],"present":[130],"hybrid":[132],"retrieval":[133,171,189,205],"pipeline":[134],"combines":[136],"embedding":[137],"text":[139],"based":[140],"searching":[141],"LLM-guided":[143],"ranking":[144],"supply":[146],"relevant":[149],"during":[152],"generation.":[154],"evaluate":[156],"impact":[158],"testing":[163],"table":[170,188],"after":[173],"being":[174],"augmented":[175],"appropriate":[177],"demonstrate":[181],"significantly":[184],"improves":[185],"accuracy":[186],"BEAVER:":[191],"enterprise-level":[193],"benchmark.":[195],"Our":[196],"findings":[197],"highlight":[198],"importance":[200],"augmentation":[206],"bringing":[208],"closer":[210],"deployment":[212],"enterprise-grade":[214],"database":[215],"systems,":[216],"common":[220],"modes":[222],"occur":[224],"when":[225],"executing":[226],"Text-to-SQL.":[228]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}