{"id":"https://openalex.org/W4389539730","doi":"https://doi.org/10.14778/3626292.3626294","title":"Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes","display_name":"Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389539730","doi":"https://doi.org/10.14778/3626292.3626294"},"language":"en","primary_location":{"id":"doi:10.14778/3626292.3626294","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3626292.3626294","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/A5075032133","display_name":"Simran Arora","orcid":"https://orcid.org/0000-0002-2087-8043"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Simran Arora","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084812990","display_name":"Brandon Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brandon Yang","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011478764","display_name":"Sabri Eyuboglu","orcid":"https://orcid.org/0000-0002-8412-0266"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sabri Eyuboglu","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039749428","display_name":"Avanika Narayan","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avanika Narayan","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091512433","display_name":"Andrew Hojel","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Hojel","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","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":false,"raw_author_name":"Immanuel Trummer","raw_affiliation_strings":["Cornell University"],"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103852640","display_name":"Christopher R\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher R\u00e9","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5075032133"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":9.6187,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.98609704,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"17","issue":"2","first_page":"92","last_page":"105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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":0.9986000061035156,"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/T11719","display_name":"Data Quality and Management","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9937999844551086,"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":0.803928017616272},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.7738176584243774},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.615996241569519},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5620302557945251},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48278892040252686},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4755382537841797},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42736685276031494},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41681498289108276},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4163736402988434},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3522011339664459},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3418298661708832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3413258194923401},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2664951980113983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803928017616272},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.7738176584243774},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.615996241569519},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5620302557945251},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48278892040252686},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4755382537841797},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42736685276031494},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41681498289108276},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4163736402988434},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3522011339664459},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3418298661708832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3413258194923401},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2664951980113983},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3626292.3626294","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3626292.3626294","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1489949474","https://openalex.org/W1934084512","https://openalex.org/W1980640510","https://openalex.org/W2115461474","https://openalex.org/W2127978399","https://openalex.org/W2138334515","https://openalex.org/W2148540243","https://openalex.org/W2161861392","https://openalex.org/W2340222647","https://openalex.org/W2540700336","https://openalex.org/W2560674852","https://openalex.org/W2740887992","https://openalex.org/W2769041395","https://openalex.org/W2911424454","https://openalex.org/W2917458986","https://openalex.org/W2959716049","https://openalex.org/W3103433205","https://openalex.org/W3118781290","https://openalex.org/W3203321135","https://openalex.org/W4248809068","https://openalex.org/W4312537169","https://openalex.org/W4315631901","https://openalex.org/W4321448364","https://openalex.org/W4322708560","https://openalex.org/W4385573087"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W4381094582","https://openalex.org/W1978893398","https://openalex.org/W1977906818","https://openalex.org/W2201908702","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1522139108","https://openalex.org/W2353528968","https://openalex.org/W2600085362"],"abstract_inverted_index":{"A":[0],"long":[1],"standing":[2],"goal":[3],"in":[4,183],"the":[5,23,52,81,91,98,124,163,172,175,184,188],"data":[6],"management":[7],"community":[8],"is":[9,112,148],"developing":[10],"systems":[11,31,166],"that":[12,96],"input":[13],"documents":[14,88,173,187],"and":[15,35,63,154],"output":[16],"queryable":[17],"tables":[18],"without":[19],"user":[20],"effort.":[21],"Given":[22],"sheer":[24],"variety":[25],"of":[26,56,186],"potential":[27],"documents,":[28],"state-of-the":[29,164],"art":[30,165],"make":[32],"simplifying":[33],"assumptions":[34],"use":[36],"domain":[37],"specific":[38],"training.":[39],"In":[40],"this":[41,78],"work,":[42],"we":[43,46,133],"ask":[44],"whether":[45],"can":[47],"maintain":[48],"generality":[49],"by":[50,70],"using":[51,158,167],"in-context":[53],"learning":[54],"abilities":[55],"large":[57],"language":[58],"models":[59],"(LLMs).":[60],"We":[61,72],"propose":[62,134],"evaluate":[64],"Evaporate,":[65],"a":[66,103,168,180],"prototype":[67],"system":[68],"powered":[69],"LLMs.":[71],"identify":[73],"two":[74,108],"strategies":[75],"for":[76],"implementing":[77],"system:":[79],"prompt":[80,90],"LLM":[82,92,189],"to":[83,93,149,179,191],"directly":[84,119],"extract":[85],"values":[86],"from":[87],"or":[89],"synthesize":[94],"code":[95],"performs":[97],"extraction.":[99,145],"Our":[100,146],"evaluations":[101],"show":[102],"cost-quality":[104],"tradeoff":[105],"between":[106],"these":[107],"approaches.":[109],"Code":[110],"synthesis":[111],"cheap,":[113],"but":[114],"far":[115],"less":[116],"accurate":[117],"than":[118,143],"processing":[120],"each":[121],"document":[122],"with":[123,174],"LLM.":[125,176],"To":[126],"improve":[127],"quality":[128,142],"while":[129],"maintaining":[130],"low":[131],"cost,":[132],"an":[135],"extended":[136],"implementation,":[137],"Evaporate-Code+,":[138],"which":[139],"achieves":[140],"better":[141],"direct":[144],"insight":[147],"generate":[150],"many":[151],"candidate":[152],"functions":[153],"ensemble":[155],"their":[156],"extractions":[157],"weak":[159],"supervision.":[160],"Evaporate-Code+":[161],"outperforms":[162],"sublinear":[169],"pass":[170],"over":[171],"This":[177],"equates":[178],"110X":[181],"reduction":[182],"number":[185],"needs":[190],"process":[192],"across":[193],"our":[194],"16":[195],"real-world":[196],"evaluation":[197],"settings.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":9}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}