{"id":"https://openalex.org/W7160521231","doi":"https://doi.org/10.48550/arxiv.2605.04911","title":"Breaking the Quality-Privacy Tradeoff in Tabular Data Generation via In-Context Learning","display_name":"Breaking the Quality-Privacy Tradeoff in Tabular Data Generation via In-Context Learning","publication_year":2026,"publication_date":"2026-05-06","ids":{"openalex":"https://openalex.org/W7160521231","doi":"https://doi.org/10.48550/arxiv.2605.04911"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.04911","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04911","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.04911","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5131202419","display_name":"Xinyan Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Xinyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135604970","display_name":"Yan Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135608230","display_name":"Xiaoyu Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135622557","display_name":"Yuanyuan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Yuanyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133231653","display_name":"Yuanrui Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuanrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135608767","display_name":"Xuanyue Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xuanyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135605364","display_name":"Wenchao Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Wenchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135566637","display_name":"Xingxuan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xingxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.65420001745224,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.65420001745224,"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":0.05490000173449516,"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/T11719","display_name":"Data Quality and Management","score":0.03869999945163727,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5989000201225281},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5587999820709229},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5238999724388123},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5041000247001648},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.48500001430511475},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.4828999936580658},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4672999978065491},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4634000062942505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8159999847412109},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5989000201225281},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5587999820709229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5264999866485596},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5001999735832214},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.48500001430511475},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45739999413490295},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.43689998984336853},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.412200003862381},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C2780977526","wikidata":"https://www.wikidata.org/wiki/Q42417149","display_name":"Data exploration","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.04911","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04911","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.04911","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04911","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tabular":[0],"data":[1,7,28,75,104,127,134,138],"synthesis":[2],"aims":[3],"to":[4,59,102],"generate":[5,132],"high-quality":[6],"while":[8],"preserving":[9],"privacy.":[10],"However,":[11],"we":[12,69],"find":[13],"that":[14,123,135,143],"existing":[15],"tabular":[16,74],"generative":[17,57],"models":[18,58],"exhibit":[19],"a":[20,95],"clear":[21],"tradeoff":[22,46,146],"in":[23],"the":[24,33,144],"small-data":[25],"regime:":[26],"improving":[27],"quality":[29,128],"typically":[30],"comes":[31],"at":[32],"cost":[34],"of":[35,38,83,98],"increased":[36],"memorization":[37],"training":[39,50,152],"samples,":[40],"thereby":[41],"weakening":[42],"privacy":[43],"protection.":[44],"This":[45],"arises":[47],"because":[48],"small":[49],"sets":[51],"make":[52],"it":[53,101],"difficult":[54],"for":[55],"dataset-specific":[56],"distinguish":[60],"generalizable":[61],"structure":[62],"from":[63,87,94,106],"sample-specific":[64],"patterns.":[65],"To":[66],"address":[67],"this,":[68],"propose":[70],"DiffICL,":[71],"which":[72],"formulates":[73],"generation":[76],"as":[77],"an":[78],"in-context":[79],"learning":[80],"problem.":[81],"Instead":[82],"fitting":[84],"each":[85],"dataset":[86],"scratch,DiffICL":[88],"leverages":[89],"pretrained":[90],"structural":[91],"priors":[92],"learned":[93],"large":[96],"collection":[97],"datasets,":[99],"enabling":[100],"infer":[103],"distributions":[105],"limited":[107],"context":[108],"rather":[109],"than":[110],"memorizing":[111],"individual":[112],"samples.":[113],"We":[114],"evaluate":[115],"DiffICL":[116,124],"on":[117],"14":[118],"real-world":[119],"datasets.":[120],"Results":[121],"show":[122],"improves":[125],"both":[126],"and":[129,131],"privacy,":[130],"synthetic":[133],"provides":[136],"effective":[137],"augmentation.":[139],"Our":[140],"findings":[141],"suggest":[142],"quality-privacy":[145],"can":[147],"be":[148],"improved":[149],"through":[150],"better":[151],"paradigms.":[153]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-08T00:00:00"}