{"id":"https://openalex.org/W7166870473","doi":"https://doi.org/10.18653/v1/2026.acl-long.1008","title":"SelFusion: Self-distillation for Diffusion Language Models","display_name":"SelFusion: Self-distillation for Diffusion Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166870473","doi":"https://doi.org/10.18653/v1/2026.acl-long.1008"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1008","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1008","pdf_url":"https://aclanthology.org/2026.acl-long.1008.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.1008.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125763600","display_name":"Hyeongsoo Lim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyeongsoo Lim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134372290","display_name":"Jinyoung Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyoung Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015801686","display_name":"Eun Seo Seo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eun Seo Seo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129706163","display_name":"Min Ho Jang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Ho Jang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139784941","display_name":"Ji Won Yoon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji Won Yoon","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.91065831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22077","last_page":"22089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.17260000109672546,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.17260000109672546,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.11760000139474869,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.06669999659061432,"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/diffusion","display_name":"Diffusion","score":0.3443000018596649},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.26739999651908875},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.2660999894142151},{"id":"https://openalex.org/keywords/coupling","display_name":"Coupling (piping)","score":0.2547999918460846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5029000043869019},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32600000500679016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30059999227523804},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.2842000126838684},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.27480000257492065},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1008","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1008","pdf_url":"https://aclanthology.org/2026.acl-long.1008.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.1008","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1008","pdf_url":"https://aclanthology.org/2026.acl-long.1008.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":[{"id":"https://openalex.org/G13572568","display_name":null,"funder_award_id":"RS-2021-II211341","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4244160943","display_name":null,"funder_award_id":"RS-2021-II211341","funder_id":"https://openalex.org/F4320321202","funder_display_name":"Chung-Ang University"},{"id":"https://openalex.org/G552592315","display_name":null,"funder_award_id":"RS-2021-II211341","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321202","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166870473.pdf","grobid_xml":"https://content.openalex.org/works/W7166870473.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"language":[1,13],"models":[2,14],"(DLMs)":[3],"alleviate":[4],"the":[5,83,92,100,109,124,131,144,160,167,170],"inherent":[6],"latency":[7],"bottleneck":[8],"of":[9,169],"autoregressive":[10],"(AR)":[11],"large":[12],"(LLMs),":[15],"but":[16],"their":[17],"degraded":[18],"generation":[19,50,180],"quality":[20],"limits":[21],"practical":[22,175],"applicability.Although":[23],"knowledge":[24],"distillation":[25,132],"(KD)":[26],"can":[27,113,128],"be":[28,114],"a":[29,57,87,96,174],"promising":[30],"direction":[31,133],"for":[32,61],"improving":[33,178],"performance,":[34],"we":[35,55,119],"empirically":[36],"find":[37],"that":[38,143],"naively":[39],"applying":[40],"conventional":[41],"KD":[42,67,122,150],"yields":[43],"only":[44],"marginal":[45],"gains,":[46],"or":[47],"even":[48,165],"degrades":[49],"quality.Based":[51],"on":[52,116,135,139],"these":[53],"observations,":[54],"propose":[56],"novel":[58],"self-distillation":[59,146],"framework":[60],"DLMs,":[62],"namely":[63],"SelFusion.To":[64],"enable":[65],"effective":[66],"without":[68],"an":[69],"external":[70,153],"teacher":[71],"model,":[72],"SelFusion":[73,164],"performs":[74],"two":[75,125],"forward":[76],"passes":[77],"with":[78,86,95,152,163],"different":[79],"masking":[80,89,98],"levels,":[81],"defining":[82],"hard":[84,110],"mode":[85,94,102,111],"larger":[88],"probability":[90],"and":[91,112,155],"easy":[93,101],"smaller":[97],"probability.However,":[99],"is":[103],"not":[104],"always":[105],"more":[106],"accurate":[107],"than":[108],"overconfident":[115],"incorrect":[117],"tokens.Thus,":[118],"introduce":[120],"bidirectional":[121],"between":[123],"modes,":[126],"which":[127],"dynamically":[129],"determine":[130],"based":[134],"token-level":[136],"correctness.Experimental":[137],"results":[138],"instruction-following":[140],"tasks":[141],"show":[142],"proposed":[145],"substantially":[147],"outperforms":[148],"other":[149],"methods":[151],"LLM":[154,171],"DLM":[156,179],"teachers.In":[157],"many":[158],"configurations,":[159],"student":[161],"trained":[162],"surpasses":[166],"performance":[168],"teacher,":[172],"providing":[173],"path":[176],"toward":[177],"quality.":[181]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}