{"id":"https://openalex.org/W7140120779","doi":"https://doi.org/10.18653/v1/2026.eacl-srw.13","title":"Beyond One-Step Distillation: Bridging the Capacity Gap in Small Language Models via Multi-Step Knowledge Transfer","display_name":"Beyond One-Step Distillation: Bridging the Capacity Gap in Small Language Models via Multi-Step Knowledge Transfer","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140120779","doi":"https://doi.org/10.18653/v1/2026.eacl-srw.13"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-srw.13","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-srw.13","pdf_url":"https://aclanthology.org/2026.eacl-srw.13.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-srw.13.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130334536","display_name":"Gaeun Yim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaeun Yim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130366407","display_name":"Nayoung Ko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nayoung Ko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130408824","display_name":"Manasa Bharadwaj","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manasa Bharadwaj","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":0.25343122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"182","last_page":"187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.23839999735355377,"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":0.23839999735355377,"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":0.19760000705718994,"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/T13629","display_name":"Text Readability and Simplification","score":0.10159999877214432,"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/bridging","display_name":"Bridging (networking)","score":0.7766000032424927},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.4634000062942505},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.32409998774528503},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.3003999888896942},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.29989999532699585}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7766000032424927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5702999830245972},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3544999957084656},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.32749998569488525},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26420000195503235},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-srw.13","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-srw.13","pdf_url":"https://aclanthology.org/2026.eacl-srw.13.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-srw.13","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-srw.13","pdf_url":"https://aclanthology.org/2026.eacl-srw.13.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1248055536","display_name":null,"funder_award_id":"RS-2022-00143911","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140120779.pdf","grobid_xml":"https://content.openalex.org/works/W7140120779.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1,115],"Models":[2,116],"(LLMs)":[3],"excel":[4],"across":[5,69],"diverse":[6],"NLP":[7],"tasks":[8],"but":[9],"remain":[10],"too":[11],"large":[12,29],"for":[13,107],"efficient":[14],"on-device":[15],"deployment.Although":[16],"knowledge":[17,51,68],"distillation":[18,26,52],"is":[19],"a":[20,28,32,102],"promising":[21],"compression":[22],"strategy,":[23],"direct":[24],"one-step":[25],"from":[27],"teacher":[30,67],"to":[31,37,42],"small":[33],"student":[34],"often":[35],"leads":[36],"substantial":[38],"performance":[39],"loss":[40],"due":[41],"the":[43],"capacity":[44],"gap.In":[45],"this":[46],"work,":[47],"we":[48,80],"revisit":[49],"multi-step":[50,99],"(MSKD)":[53],"as":[54,101],"an":[55],"effective":[56],"remedy,":[57],"exploring":[58],"how":[59],"staged,":[60],"size-aware":[61],"transfer":[62,100],"paths":[63],"can":[64],"better":[65],"preserve":[66],"students":[70],"of":[71],"varying":[72],"scales.Through":[73],"extensive":[74],"experiments":[75],"with":[76],"GPT-2":[77],"and":[78,87],"OPT,":[79],"demonstrate":[81],"that":[82],"MSKD":[83],"always":[84],"improves":[85],"perplexity":[86],"ROUGE-L":[88],"score":[89],"over":[90],"single-step":[91],"approaches":[92],"without":[93],"requiring":[94],"specialized":[95],"finetuning.Our":[96],"results":[97],"establish":[98],"simple":[103],"yet":[104],"powerful":[105],"framework":[106],"progressively":[108],"compressing":[109],"LLMs":[110],"into":[111],"efficient,":[112],"highperforming":[113],"Small":[114],"(SLMs).":[117]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-24T00:00:00"}