{"id":"https://openalex.org/W4412944783","doi":"https://doi.org/10.18653/v1/2025.acl-long.1097","title":"Towards the Law of Capacity Gap in Distilling Language Models","display_name":"Towards the Law of Capacity Gap in Distilling Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944783","doi":"https://doi.org/10.18653/v1/2025.acl-long.1097"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1097","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd 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":"green","oa_url":"https://curis.ku.dk/ws/files/535477451/Towards_the_Law_of_Capacity_Gap.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100374113","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0002-3306-9317"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026465666","display_name":"Qiuchi Li","orcid":"https://orcid.org/0000-0002-8219-0869"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiuchi Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050532724","display_name":"Dawei Song","orcid":"https://orcid.org/0000-0002-8660-3608"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dawei Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109655731","display_name":"Zheyu Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheyu Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111520174","display_name":"Yan Gao","orcid":"https://orcid.org/0000-0002-4686-6315"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5104228339","display_name":"Yao Hu","orcid":"https://orcid.org/0009-0002-0651-8487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Hu","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":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22504","last_page":"22528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9366000294685364,"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":0.9366000294685364,"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/computer-science","display_name":"Computer science","score":0.562495231628418},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.33545607328414917},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.17721712589263916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.562495231628418},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.33545607328414917},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.17721712589263916}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1097","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/3d9ef34f-9c87-4164-ae7f-782e05e2f2d0","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/3d9ef34f-9c87-4164-ae7f-782e05e2f2d0","pdf_url":"https://curis.ku.dk/ws/files/535477451/Towards_the_Law_of_Capacity_Gap.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/3d9ef34f-9c87-4164-ae7f-782e05e2f2d0","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/3d9ef34f-9c87-4164-ae7f-782e05e2f2d0","pdf_url":"https://curis.ku.dk/ws/files/535477451/Towards_the_Law_of_Capacity_Gap.pdf","source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4853011787","display_name":null,"funder_award_id":"62376027","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944783.pdf","grobid_xml":"https://content.openalex.org/works/W4412944783.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Language":[0],"model":[1,157],"(LM)":[2],"distillation":[3,88,167],"aims":[4],"at":[5],"distilling":[6,136],"the":[7,46,53,63,77,81,85,103,111,125,145,152,163],"knowledge":[8],"in":[9,45,110,175],"a":[10,15,20,26,32,35,41,93,132,137,169,181],"large":[11,114],"teacher":[12,33,54,75,147],"LM":[13,24],"to":[14,61,101,165],"small":[16,37],"student":[17,28,79,153],"one.":[18],"As":[19],"critical":[21,121],"issue":[22],"facing":[23],"distillation,":[25],"superior":[27],"often":[29,59],"arises":[30],"from":[31,131],"of":[34,40,48,65,84,92,96,113,127,140,184],"relatively":[36],"scale":[38,154,171],"instead":[39],"larger":[42,170],"one,":[43],"especially":[44],"presence":[47],"substantial":[49],"capacity":[50,66,128],"gap":[51,129],"between":[52],"and":[55,158],"student.":[56],"This":[57,117],"issue,":[58],"referred":[60],"as":[62],"curse":[64],"gap,":[67],"suggests":[68],"that":[69,179],"there":[70],"is":[71],"likely":[72],"an":[73],"optimal":[74,104,146],"yielding":[76],"best-performing":[78],"along":[80],"scaling":[82],"course":[83],"teacher.":[86],"Consequently,":[87],"trials":[89],"on":[90,135,168],"teachers":[91],"wide":[94,182],"range":[95,139],"scales":[97,149],"are":[98],"called":[99],"for":[100],"determine":[102],"teacher,":[105],"which":[106],"becomes":[107],"computationally":[108],"intensive":[109],"context":[112],"LMs":[115],"(LLMs).":[116],"paper":[118],"addresses":[119],"this":[120],"bottleneck":[122],"by":[123],"providing":[124],"law":[126,164],"inducted":[130],"preliminary":[133],"study":[134],"broad":[138],"small-scale":[141],"(<3B)":[142],"LMs,":[143],"where":[144],"consistently":[148],"linearly":[150],"with":[151],"across":[155],"different":[156],"data":[159],"scales.":[160],"By":[161],"extending":[162],"LLM":[166],"(7B),":[172],"we":[173],"succeed":[174],"obtaining":[176],"versatile":[177],"LLMs":[178],"outperform":[180],"array":[183],"competitors.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}