{"id":"https://openalex.org/W7166877718","doi":"https://doi.org/10.18653/v1/2026.acl-long.174","title":"SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation","display_name":"SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166877718","doi":"https://doi.org/10.18653/v1/2026.acl-long.174"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.174","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.174","pdf_url":"https://aclanthology.org/2026.acl-long.174.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.174.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139757557","display_name":"Shuo Yang","orcid":null},"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":"Shuo Yang","raw_affiliation_strings":["Technical University of Munich Munich Center for Machine Learning (MCML"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich Munich Center for Machine Learning (MCML","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139843959","display_name":"Zheyu Zhang","orcid":null},"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":"Zheyu Zhang","raw_affiliation_strings":["Technical University of Munich Munich Center for Machine Learning (MCML"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich Munich Center for Machine Learning (MCML","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017702643","display_name":"Bardh Prenkaj","orcid":"https://orcid.org/0000-0002-2991-2279"},"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":"Bardh Prenkaj","raw_affiliation_strings":["Technical University of Munich Munich Center for Machine Learning (MCML"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich Munich Center for Machine Learning (MCML","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024434748","display_name":"Gjergji Kasneci","orcid":null},"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":"Gjergji Kasneci","raw_affiliation_strings":["Technical University of Munich Munich Center for Machine Learning (MCML"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich Munich Center for Machine Learning (MCML","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87175377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3792","last_page":"3807"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.05609999969601631,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.05609999969601631,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.052799999713897705,"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"}},{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.03550000116229057,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.27309998869895935},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26930001378059387},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.2483000010251999},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.23970000445842743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5611000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.429500013589859},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3034999966621399},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27309998869895935},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2483000010251999},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.24709999561309814},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.23970000445842743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2387000024318695}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.174","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.174","pdf_url":"https://aclanthology.org/2026.acl-long.174.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.174","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.174","pdf_url":"https://aclanthology.org/2026.acl-long.174.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166877718.pdf","grobid_xml":"https://content.openalex.org/works/W7166877718.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"high-fidelity":[1],"synthetic":[2],"tabular":[3,158],"data":[4,11,127,159],"remains":[5],"a":[6,66,85],"critical":[7],"challenge":[8],"for":[9],"enhancing":[10],"availability":[12],"in":[13,157],"privacy-sensitive":[14],"and":[15,41,74,83,118,129,161],"lowresource":[16],"domains.Recent":[17],"approaches":[18],"leverage":[19],"LLMs":[20,104],"by":[21,135,147],"representing":[22],"table":[23],"rows":[24],"as":[25],"sequences,":[26],"yet":[27],"suffer":[28],"from":[29],"two":[30],"fundamental":[31],"limitations:(1)":[32],"they":[33,43],"model":[34],"feature":[35,55],"dependencies":[36,52],"densely,":[37],"introducing":[38],"spurious":[39],"correlations;":[40],"(2)":[42],"assume":[44],"static":[45],"relationships":[46],"between":[47],"features,":[48],"ignoring":[49],"how":[50],"these":[51,58],"vary":[53],"with":[54],"values.To":[56],"overcome":[57],"limitations,":[59],"we":[60],"introduce":[61],"SAGE":[62,123],"(Sparse":[63],"Adaptive":[64],"Guidance),":[65],"novel":[67],"LLM-based":[68,140],"generation":[69,94,160],"framework":[70],"that":[71,122],"enforces":[72],"sparse":[73,88],"dynamic":[75],"dependency":[76,89],"guidance.SAGE":[77],"discretizes":[78],"features":[79],"into":[80,165],"value-aware":[81],"pseudo-features":[82],"constructs":[84],"mutual":[86],"information-based":[87],"graph.This":[90],"graph":[91],"adaptively":[92],"guides":[93],"through":[95],"explicit":[96],"context":[97],"selection":[98],"or":[99],"implicit":[100],"logit":[101],"correction,":[102],"enabling":[103],"to":[105,138],"focus":[106],"on":[107],"truly":[108],"relevant":[109],"information":[110],"during":[111],"synthesis.Our":[112],"extensive":[113],"experiments":[114],"across":[115],"six":[116],"datasets":[117],"multiple":[119],"tasks":[120],"reveal":[121],"not":[124],"only":[125],"improves":[126],"fidelity":[128],"downstream":[130],"utility,":[131],"boosting":[132],"F1":[133],"scores":[134],"10%":[136],"compared":[137],"previous":[139],"methods,":[141],"but":[142],"also":[143],"reduces":[144],"policy":[145],"violations":[146],"one":[148],"point.These":[149],"results":[150],"highlight":[151],"the":[152],"importance":[153],"of":[154,168],"adaptive":[155],"structure":[156],"provide":[162],"new":[163],"insights":[164],"context-sensitive":[166],"control":[167],"LLMs.":[169]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}