{"id":"https://openalex.org/W7162502559","doi":"https://doi.org/10.1109/menacomm69507.2026.11532894","title":"Generating Synthetic Tabular Data Using Large and Small Language Models","display_name":"Generating Synthetic Tabular Data Using Large and Small Language Models","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7162502559","doi":"https://doi.org/10.1109/menacomm69507.2026.11532894"},"language":null,"primary_location":{"id":"doi:10.1109/menacomm69507.2026.11532894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/menacomm69507.2026.11532894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 6th Middle East and North Africa Communications Conference (MENACOMM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5137152835","display_name":"Uendi Mu\u00e7a","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137909","display_name":"Universitas Muhammadiyah Lampung","ror":"https://ror.org/03zf73d71","country_code":"ID","type":"education","lineage":["https://openalex.org/I4210137909"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Uendi Mu\u00e7a","raw_affiliation_strings":["BMW Group,UMLP,Montbéliard,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BMW Group,UMLP,Montbéliard,France","institution_ids":["https://openalex.org/I4210137909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119431035","display_name":"Hadi Koubeissy","orcid":null},"institutions":[{"id":"https://openalex.org/I1283382300","display_name":"BMW (Germany)","ror":"https://ror.org/05vs9tj88","country_code":"DE","type":"company","lineage":["https://openalex.org/I1283382300","https://openalex.org/I4210156768"]},{"id":"https://openalex.org/I4210156768","display_name":"BMW Group (Germany)","ror":"https://ror.org/044kkbh92","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210156768"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hadi Koubeissy","raw_affiliation_strings":["FEMTO-ST Institute,UMLP, BMW Group,Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FEMTO-ST Institute,UMLP, BMW Group,Munich,Germany","institution_ids":["https://openalex.org/I1283382300","https://openalex.org/I4210156768"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070973485","display_name":"Abdallah Makhoul","orcid":"https://orcid.org/0000-0003-0485-097X"},"institutions":[{"id":"https://openalex.org/I2802759292","display_name":"Franche-Comt\u00e9 \u00c9lectronique M\u00e9canique Thermique et Optique - Sciences et Technologies","ror":"https://ror.org/004fmxv66","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I2802759292","https://openalex.org/I37553959","https://openalex.org/I4210095849","https://openalex.org/I4405256580","https://openalex.org/I53262699"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Abdallah Makhoul","raw_affiliation_strings":["FEMTO-ST Institute,UMLP,Montbéliard,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FEMTO-ST Institute,UMLP,Montbéliard,France","institution_ids":["https://openalex.org/I2802759292"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.31209999322891235,"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":0.31209999322891235,"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/T10028","display_name":"Topic Modeling","score":0.08760000020265579,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.08070000261068344,"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/feature","display_name":"Feature (linguistics)","score":0.2847999930381775},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.2718000113964081},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.24480000138282776},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.23800000548362732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6256999969482422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41100001335144043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24480000138282776},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.23800000548362732},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.23080000281333923}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/menacomm69507.2026.11532894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/menacomm69507.2026.11532894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 6th Middle East and North Africa Communications Conference (MENACOMM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2099940443","https://openalex.org/W2806276686","https://openalex.org/W3033682799","https://openalex.org/W3035140194","https://openalex.org/W3035231859","https://openalex.org/W3199209662","https://openalex.org/W3202428668","https://openalex.org/W4289520498","https://openalex.org/W4383823329","https://openalex.org/W4386921320","https://openalex.org/W4397009732","https://openalex.org/W4400529822","https://openalex.org/W4402494326","https://openalex.org/W4404469447","https://openalex.org/W4405923166","https://openalex.org/W4407832462","https://openalex.org/W4411379439","https://openalex.org/W4413630082"],"related_works":[],"abstract_inverted_index":{"Synthetic":[0],"data":[1,10,71,136,167],"generation":[2],"has":[3],"become":[4],"a":[5],"key":[6],"solution":[7],"for":[8,13,91],"enabling":[9],"sharing,":[11],"accounting":[12],"privacy":[14,139],"constraints,":[15],"and":[16,31,43,58,62,76,84,104,109,114,138,169],"addressing":[17],"the":[18,66,144],"limited":[19],"availability":[20],"of":[21,68,79,119,146],"real-world":[22],"datasets,":[23],"particularly":[24],"in":[25,56,86],"tabular":[26,70,94],"format.":[27],"Conventional":[28],"statistical":[29],"models":[30,149,174],"generative":[32],"adversarial":[33],"networks":[34],"are":[35,175],"widely":[36],"used,":[37],"but":[38],"they":[39],"require":[40],"dataset-specific":[41],"preprocessing":[42],"sometimes":[44],"struggle":[45],"to":[46,150],"capture":[47],"complex":[48],"semantic":[49],"relationships":[50],"among":[51,164],"features":[52],"accurately.":[53],"Recent":[54],"advances":[55],"large":[57],"small":[59,106],"language":[60,88,107,148],"models(LLMs":[61],"SLMs)":[63],"have":[64],"improved":[65],"development":[67],"synthetic":[69,93],"by":[72],"introducing":[73],"transformer-based":[74],"architectures":[75],"textual":[77],"representations":[78],"tables.":[80],"This":[81],"paper":[82],"reviews":[83],"analyzes":[85],"detail":[87],"model-based":[89],"methods":[90],"generating":[92],"data,":[95],"focusing":[96],"on":[97,128],"state-of-the-art":[98],"approaches":[99],"such":[100],"as":[101],"GReaT,":[102],"TabuLa,":[103],"other":[105],"models,":[108],"highlighting":[110],"their":[111],"training":[112],"strategies":[113],"conditioning":[115],"mechanisms.":[116],"The":[117],"performance":[118,153],"each":[120],"model":[121,165],"across":[122],"multiple":[123],"datasets":[124],"is":[125],"evaluated":[126],"based":[127],"3":[129],"main":[130],"criteria:":[131],"downstream":[132],"machine":[133],"learning":[134],"utility,":[135],"representativeness,":[137],"preservation.":[140],"Furthermore,":[141],"we":[142],"examine":[143],"potential":[145],"smaller":[147],"achieve":[151],"competitive":[152],"with":[154],"significantly":[155],"reduced":[156],"computational":[157],"cost.":[158],"Experimental":[159],"results":[160],"show":[161],"necessary":[162],"trade-offs":[163],"size,":[166],"quality,":[168],"efficiency,":[170],"underscoring":[171],"that":[172],"larger":[173],"not":[176],"necessarily":[177],"optimal.":[178]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-05-28T00:00:00"}