{"id":"https://openalex.org/W4306178203","doi":"https://doi.org/10.48550/arxiv.2210.06280","title":"Language Models are Realistic Tabular Data Generators","display_name":"Language Models are Realistic Tabular Data Generators","publication_year":2022,"publication_date":"2022-10-12","ids":{"openalex":"https://openalex.org/W4306178203","doi":"https://doi.org/10.48550/arxiv.2210.06280"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.06280","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.06280","pdf_url":"https://arxiv.org/pdf/2210.06280","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.06280","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Borisov, Vadim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Borisov, Vadim","raw_affiliation_strings":["University of T\u00fcbingen , T\u00fcbingen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen , T\u00fcbingen , Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013346660","display_name":"Kathrin Se\u00dfler","orcid":"https://orcid.org/0000-0002-3380-4641","observed_orcids":["https://orcid.org/0000-0002-3380-4641"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Se\u00dfler, Kathrin","raw_affiliation_strings":["Technical University of Munich , Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich , Munich , Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086270771","display_name":"Tobias Leemann","orcid":"https://orcid.org/0000-0001-9333-228X","observed_orcids":["https://orcid.org/0000-0001-9333-228X"]},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Leemann, Tobias","raw_affiliation_strings":["University of T\u00fcbingen , T\u00fcbingen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen , T\u00fcbingen , Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044448837","display_name":"Martin Pawelczyk","orcid":"https://orcid.org/0000-0002-6191-4434","observed_orcids":["https://orcid.org/0000-0002-6191-4434"]},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pawelczyk, Martin","raw_affiliation_strings":["University of T\u00fcbingen , T\u00fcbingen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen , T\u00fcbingen , Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024434748","display_name":"Gjergji Kasneci","orcid":"https://orcid.org/0000-0002-3123-7268","observed_orcids":["https://orcid.org/0000-0002-3123-7268"]},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kasneci, Gjergji","raw_affiliation_strings":["University of T\u00fcbingen , T\u00fcbingen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen , T\u00fcbingen , Germany","institution_ids":["https://openalex.org/I8087733"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":68,"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":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.43650001287460327,"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":0.43650001287460327,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.31349998712539673,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.039400000125169754,"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/tabular-data-generation","display_name":"tabular data generation","score":0.9520000219345093},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"synthetic data","score":0.8389999866485596},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9760000109672546},{"id":"https://openalex.org/keywords/autoregressive-generation","display_name":"autoregressive generation","score":0.7200000286102295},{"id":"https://openalex.org/keywords/great","display_name":"GREAT","score":0.8349999785423279},{"id":"https://openalex.org/keywords/conditional-sampling","display_name":"conditional sampling","score":0.6050000190734863},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.40400001406669617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7492728233337402},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6875671148300171},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5762863159179688},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5571223497390747},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5366539359092712},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5184011459350586},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5130159258842468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4830244481563568},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.47853097319602966},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4492345452308655},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.42497822642326355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37744924426078796},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.1423128843307495},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09344297647476196},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2210.06280","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.06280","pdf_url":"https://arxiv.org/pdf/2210.06280","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.06280","doi":"https://doi.org/10.48550/arxiv.2210.06280","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.06280","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.06280","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.06280","pdf_url":"https://arxiv.org/pdf/2210.06280","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4407832462","https://openalex.org/W7162502559","https://openalex.org/W4415245799","https://openalex.org/W4415061381","https://openalex.org/W4411379439","https://openalex.org/W4415334566","https://openalex.org/W4399794317","https://openalex.org/W4405783727","https://openalex.org/W4407806916","https://openalex.org/W4413913950"],"abstract_inverted_index":{"Tabular":[0,81],"data":[1,52,103,142,159],"is":[2],"among":[3],"the":[4,13,19,35,112,122,125,135,140],"oldest":[5],"and":[6,92,137,157],"most":[7],"ubiquitous":[8],"forms":[9],"of":[10,15,79,110,124,131,139],"data.":[11,29,97],"However,":[12],"generation":[14],"synthetic":[16,91,158],"samples":[17,143],"with":[18,161],"original":[20],"data's":[21],"characteristics":[22],"remains":[23],"a":[24,129],"significant":[25],"challenge":[26],"for":[27,50],"tabular":[28,51,96,102],"While":[30],"many":[31],"generative":[32,44,69,87],"models":[33,64],"from":[34,144],"computer":[36],"vision":[37],"domain,":[38],"such":[39],"as":[40],"variational":[41],"autoencoders":[42],"or":[43],"adversarial":[45],"networks,":[46],"have":[47],"been":[48,57],"adapted":[49],"generation,":[53],"less":[54],"research":[55],"has":[56],"directed":[58],"towards":[59],"recent":[60],"transformer-based":[61],"large":[62],"language":[63],"(LLMs),":[65],"which":[66,83],"are":[67,115],"also":[68],"in":[70,128,166],"nature.":[71],"To":[72],"this":[73],"end,":[74],"we":[75],"propose":[76],"GReaT":[77,99,150],"(Generation":[78],"Realistic":[80],"data),":[82],"exploits":[84],"an":[85],"auto-regressive":[86],"LLM":[88],"to":[89],"sample":[90],"yet":[93],"highly":[94],"realistic":[95],"Furthermore,":[98],"can":[100],"model":[101],"distributions":[104],"by":[105],"conditioning":[106],"on":[107],"any":[108],"subset":[109],"features;":[111],"remaining":[113],"features":[114],"sampled":[116],"without":[117],"additional":[118],"overhead.":[119],"We":[120,147],"demonstrate":[121],"effectiveness":[123],"proposed":[126],"approach":[127],"series":[130],"experiments":[132],"that":[133,149],"quantify":[134],"validity":[136],"quality":[138],"produced":[141],"multiple":[145],"angles.":[146],"find":[148],"maintains":[151],"state-of-the-art":[152],"performance":[153],"across":[154],"numerous":[155],"real-world":[156],"sets":[160],"heterogeneous":[162],"feature":[163],"types":[164],"coming":[165],"various":[167],"sizes.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2022-10-14T00:00:00"}