{"id":"https://openalex.org/W7152510654","doi":"https://doi.org/10.1145/3774904.3792520","title":"Distribution-Aligned Synthetic Text Generation via Tail-Aware Enhancement","display_name":"Distribution-Aligned Synthetic Text Generation via Tail-Aware Enhancement","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152510654","doi":"https://doi.org/10.1145/3774904.3792520"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792520","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792520","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792520","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101925993","display_name":"Yuan Fan","orcid":"https://orcid.org/0009-0004-3712-8304"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Fan","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-3712-8304","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020335793","display_name":"Xiaoyuan Liu","orcid":"https://orcid.org/0000-0002-2625-3896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyuan Liu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China and DBAPPSecurity Co., Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2625-3896","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China and DBAPPSecurity Co., Ltd., Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103033006","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-7395-4513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["DBAPPSecurity Co., Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7395-4513","affiliations":[{"raw_affiliation_string":"DBAPPSecurity Co., Ltd., Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044096889","display_name":"Wubing Wang","orcid":"https://orcid.org/0009-0002-5954-8954"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wubing Wang","raw_affiliation_strings":["DBAPPSecurity Co., Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-5954-8954","affiliations":[{"raw_affiliation_string":"DBAPPSecurity Co., Ltd., Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jia Sun","orcid":"https://orcid.org/0009-0009-4235-2913"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Sun","raw_affiliation_strings":["DBAPPSecurity Co., Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-4235-2913","affiliations":[{"raw_affiliation_string":"DBAPPSecurity Co., Ltd., Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123906545","display_name":"Wenzhi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhi Chen","raw_affiliation_strings":["computer science and Technology, Zhejiang University, hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1674-4701","affiliations":[{"raw_affiliation_string":"computer science and Technology, Zhejiang University, hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133262719","display_name":"Huaikang Fang","orcid":"https://orcid.org/0009-0005-0947-563X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaikang Fang","raw_affiliation_strings":["DBAPPSecurity Co., Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-0947-563X","affiliations":[{"raw_affiliation_string":"DBAPPSecurity Co., Ltd., Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133278429","display_name":"Lifeng Tao","orcid":"https://orcid.org/0009-0008-5281-8513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lifeng Tao","raw_affiliation_strings":["DBAPPSecurity Co., Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-5281-8513","affiliations":[{"raw_affiliation_string":"DBAPPSecurity Co., Ltd., Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Fan Mo","orcid":"https://orcid.org/0009-0005-2597-6004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan Mo","raw_affiliation_strings":["Zhejiang University, Hangzhou, China and DBAPPSecurity Co., Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-2597-6004","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China and DBAPPSecurity Co., Ltd., Hangzhou, China","institution_ids":[]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3240","last_page":"3250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2101999968290329,"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":0.2101999968290329,"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":0.1460999995470047,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.08110000193119049,"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":0.2671000063419342},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2563000023365021},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.24729999899864197},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.23569999635219574},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.21940000355243683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5529000163078308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4083000123500824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2992999851703644},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.24729999899864197},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.23569999635219574},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.21940000355243683},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.219200000166893},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.21850000321865082}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792520","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792520","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792520","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792520","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1873763122","https://openalex.org/W2109426455","https://openalex.org/W2141799614","https://openalex.org/W2962933664","https://openalex.org/W3011309387","https://openalex.org/W3120940860","https://openalex.org/W4205228770","https://openalex.org/W4206162816","https://openalex.org/W4214640945","https://openalex.org/W4231068634","https://openalex.org/W4288057780","https://openalex.org/W4292793911","https://openalex.org/W4313180564","https://openalex.org/W4388505346","https://openalex.org/W4389518932","https://openalex.org/W4391582461","https://openalex.org/W4400949264","https://openalex.org/W4402264416","https://openalex.org/W4402669773","https://openalex.org/W4406810072","https://openalex.org/W4407950371","https://openalex.org/W7133211372"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"generative":[3],"AI":[4],"have":[5],"popularized":[6],"synthetic":[7,32,59],"content":[8],"for":[9],"training,":[10],"offering":[11],"a":[12],"practical":[13],"alternative":[14],"to":[15],"costly":[16],"data":[17,33],"curation":[18],"while":[19],"addressing":[20],"privacy":[21],"concerns.":[22],"However,":[23],"accumulating":[24],"evidence":[25],"shows":[26],"that":[27,40],"the":[28,42,61,65],"indiscriminate":[29],"reuse":[30],"of":[31,64,79],"can":[34],"induce":[35],"model":[36],"collapse\u2014a":[37],"degenerative":[38],"process":[39],"contracts":[41],"learned":[43],"distribution":[44,67],"and":[45],"erodes":[46],"rare":[47],"features.":[48],"For":[49],"instance,":[50],"when":[51],"models":[52],"are":[53],"iteratively":[54],"trained":[55],"on":[56],"their":[57],"own":[58],"outputs,":[60],"upper":[62],"tail":[63],"perplexity":[66],"substantially":[68],"compresses,":[69],"with":[70],"high-percentile":[71],"values":[72],"dropping":[73],"by":[74],"nearly":[75],"half\u2014a":[76],"clear":[77],"indicator":[78],"severe":[80],"diversity":[81],"loss.":[82]},"counts_by_year":[],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2026-04-10T00:00:00"}