{"id":"https://openalex.org/W4402043024","doi":"https://doi.org/10.14778/3681954.3682017","title":"Generating Succinct Descriptions of Database Schemata for Cost-Efficient Prompting of Large Language Models","display_name":"Generating Succinct Descriptions of Database Schemata for Cost-Efficient Prompting of Large Language Models","publication_year":2024,"publication_date":"2024-07-01","ids":{"openalex":"https://openalex.org/W4402043024","doi":"https://doi.org/10.14778/3681954.3682017"},"language":"en","primary_location":{"id":"doi:10.14778/3681954.3682017","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3681954.3682017","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087259526","display_name":"Immanuel Trummer","orcid":"https://orcid.org/0000-0002-7203-2349"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Immanuel Trummer","raw_affiliation_strings":["Cornell University, Ithaca, New York, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, New York, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5087259526"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":2.1431,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.89150334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"17","issue":"11","first_page":"3511","last_page":"3523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9998000264167786,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9998000264167786,"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":0.9991999864578247,"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":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.7231066823005676},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4426153302192688},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.41836944222450256},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.387011855840683},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35931849479675293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7231066823005676},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4426153302192688},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.41836944222450256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.387011855840683},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35931849479675293}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3681954.3682017","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3681954.3682017","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2008896880","https://openalex.org/W2032374895","https://openalex.org/W2072530859","https://openalex.org/W2083658889","https://openalex.org/W2101787379","https://openalex.org/W2125605956","https://openalex.org/W2130742187","https://openalex.org/W2153084230","https://openalex.org/W2281341896","https://openalex.org/W2341078838","https://openalex.org/W2890431379","https://openalex.org/W2918000614","https://openalex.org/W3029187551","https://openalex.org/W3086973390","https://openalex.org/W3098267758","https://openalex.org/W3165814564","https://openalex.org/W3175818566","https://openalex.org/W4243637616","https://openalex.org/W4248260714","https://openalex.org/W4282566685","https://openalex.org/W4321448364","https://openalex.org/W4385573003","https://openalex.org/W4386566526","https://openalex.org/W4389519226","https://openalex.org/W4390493562","https://openalex.org/W4396571402","https://openalex.org/W4401043020","https://openalex.org/W6831490475"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Using":[0],"large":[1],"language":[2],"models":[3,90],"(LLMs)":[4],"for":[5,147],"tasks":[6,155],"like":[7],"text-to-SQL":[8,158],"translation":[9],"often":[10],"requires":[11],"describing":[12],"the":[13,19,30,37,40,123,152],"database":[14,63],"schema":[15,41,70,86,91,140],"as":[16,26,93,157],"part":[17],"of":[18,29,32,39,61],"model":[20,47],"input.":[21],"LLM":[22],"providers":[23],"typically":[24,76],"charge":[25],"a":[27,53,94],"function":[28],"number":[31],"tokens":[33,83],"read.":[34],"Hence,":[35],"reducing":[36,122,151],"length":[38,142],"description":[42,141],"saves":[43],"money":[44],"at":[45],"each":[46],"invocation.":[48],"This":[49],"paper":[50],"introduces":[51],"Schemonic,":[52],"system":[54],"that":[55,79,137],"automatically":[56],"finds":[57,77],"concise":[58],"text":[59],"descriptions":[60,78],"relational":[62],"schemata.":[64],"By":[65],"introducing":[66],"abbreviations":[67],"or":[68,108],"grouping":[69],"elements":[71],"with":[72,145],"similar":[73],"properties,":[74],"Schemonic":[75,89,138],"use":[80],"significantly":[81],"fewer":[82],"than":[84],"naive":[85],"representations.":[87],"Internally,":[88],"compression":[92],"combinatorial":[95],"optimization":[96,114,117],"problem":[97],"and":[98,121,134],"uses":[99],"integer":[100],"linear":[101],"programming":[102],"solvers":[103],"to":[104],"find":[105],"guaranteed":[106],"optimal":[107],"near-optimal":[109],"solutions.":[110],"It":[111],"speeds":[112],"up":[113],"by":[115],"starting":[116],"from":[118],"heuristic":[119],"solutions":[120],"search":[124],"space":[125],"size":[126],"via":[127],"pre-processing.":[128],"The":[129],"experiments":[130],"on":[131],"TPC-H,":[132],"SPIDER,":[133],"Public-BI":[135],"demonstrate":[136],"reduces":[139],"significantly,":[143],"along":[144],"fees":[146],"reading":[148],"them,":[149],"without":[150],"accuracy":[153],"in":[154],"such":[156],"translation.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}