{"id":"https://openalex.org/W4412888790","doi":"https://doi.org/10.18653/v1/2025.findings-acl.87","title":"Group then Scale: Dynamic Mixture-of-Experts Multilingual Language Model","display_name":"Group then Scale: Dynamic Mixture-of-Experts Multilingual Language Model","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888790","doi":"https://doi.org/10.18653/v1/2025.findings-acl.87"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.87","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.87","pdf_url":"https://aclanthology.org/2025.findings-acl.87.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.87.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100412259","display_name":"Chong Li","orcid":"https://orcid.org/0009-0000-0708-7493"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120698131","display_name":"Yingzhuo Deng","orcid":"https://orcid.org/0000-0001-9286-2123"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingzhuo Deng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319572","display_name":"Jiajun Zhang","orcid":"https://orcid.org/0000-0001-5293-7434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajun Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015785439","display_name":"Chengqing Zong","orcid":"https://orcid.org/0000-0002-9864-3818"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengqing Zong","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1730","last_page":"1754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7921000123023987,"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/T10028","display_name":"Topic Modeling","score":0.7921000123023987,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.7662000060081482,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7369933128356934},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5979057550430298},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5354782342910767},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.4712769389152527},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4326595366001129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38244301080703735}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7369933128356934},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5979057550430298},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5354782342910767},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.4712769389152527},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4326595366001129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38244301080703735},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.87","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.87","pdf_url":"https://aclanthology.org/2025.findings-acl.87.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.87","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.87","pdf_url":"https://aclanthology.org/2025.findings-acl.87.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6299999952316284,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1883487206","display_name":null,"funder_award_id":"62336008","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"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888790.pdf","grobid_xml":"https://content.openalex.org/works/W4412888790.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W3093517588"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2184221808","https://openalex.org/W2740147593","https://openalex.org/W2547800031","https://openalex.org/W4247431094","https://openalex.org/W3200324093","https://openalex.org/W2352386950","https://openalex.org/W3188962172","https://openalex.org/W4230573045","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"curse":[1],"of":[2,9,51,103],"multilinguality":[3],"phenomenon":[4],"is":[5,63],"a":[6,41],"fundamental":[7],"problem":[8],"multilingual":[10,52,125,147],"Large":[11],"Language":[12],"Models":[13],"(LLMs),":[14],"where":[15,96],"the":[16,49,61,71,79,117,136,142,145],"competition":[17,93],"between":[18,33,81,94,120],"massive":[19],"languages":[20,111,121],"results":[21,106],"in":[22,74],"inferior":[23],"performance.It":[24],"mainly":[25],"comes":[26],"from":[27],"limited":[28],"capacity":[29],"and":[30,46,77,122,140],"negative":[31,118],"transfer":[32,57,119],"dissimilar":[34],"languages.To":[35],"address":[36],"this":[37],"issue,":[38],"we":[39],"propose":[40],"method":[42,115],"to":[43,69,88,91,109],"dynamically":[44],"group":[45,102,131],"scale":[47],"up":[48],"parameters":[50],"LLM":[53],"while":[54],"boosting":[55],"positive":[56],"among":[58],"similar":[59,104],"languages.Specifically,":[60],"model":[62],"first":[64],"tuned":[65],"on":[66,107,133,144],"monolingual":[67],"corpus":[68],"determine":[70],"parameter":[72],"deviation":[73],"each":[75],"layer":[76],"quantify":[78],"similarity":[80],"languages.Layers":[82],"with":[83,127],"more":[84],"deviations":[85],"are":[86],"extended":[87],"mixture-of-experts":[89],"layers":[90],"reduce":[92],"languages,":[95],"one":[97,101],"expert":[98],"module":[99],"serves":[100],"languages.Experimental":[105],"18":[108],"128":[110],"show":[112],"that":[113],"our":[114],"reduces":[116,141],"significantly":[123],"boosts":[124],"performance":[126],"fewer":[128],"parameters.Such":[129],"language":[130,138],"specialization":[132],"experts":[134],"benefits":[135],"new":[137],"adaptation":[139],"inference":[143],"previous":[146],"knowledge":[148],"learned.":[149]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}