{"id":"https://openalex.org/W4412888757","doi":"https://doi.org/10.18653/v1/2025.findings-acl.221","title":"Scaling Laws for Multilingual Language Models","display_name":"Scaling Laws for Multilingual Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888757","doi":"https://doi.org/10.18653/v1/2025.findings-acl.221"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.221","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.221","pdf_url":"https://aclanthology.org/2025.findings-acl.221.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.221.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004554042","display_name":"Yifei He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifei He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011785041","display_name":"Alon Benhaim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alon Benhaim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076387701","display_name":"Barun Patra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barun Patra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086111928","display_name":"Praneetha Vaddamanu","orcid":"https://orcid.org/0000-0003-4894-9517"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Praneetha Vaddamanu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044946466","display_name":"Sumati Ahuja","orcid":"https://orcid.org/0000-0003-0841-7671"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanchit Ahuja","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003848348","display_name":"Parul Chopra","orcid":"https://orcid.org/0000-0001-5852-944X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parul Chopra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053028004","display_name":"Vishrav Chaudhary","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vishrav Chaudhary","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108581824","display_name":"Han Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101027890","display_name":"Xia Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87776052,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4257","last_page":"4273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9430999755859375,"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":0.9430999755859375,"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/scaling-law","display_name":"Scaling law","score":0.6422946453094482},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6348064541816711},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5115050077438354},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41971972584724426},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3486475348472595},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.3466337323188782},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.24106758832931519},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1462293267250061},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.12465322017669678},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.07044234871864319}],"concepts":[{"id":"https://openalex.org/C2988430800","wikidata":"https://www.wikidata.org/wiki/Q428971","display_name":"Scaling law","level":3,"score":0.6422946453094482},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6348064541816711},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5115050077438354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41971972584724426},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3486475348472595},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.3466337323188782},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.24106758832931519},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1462293267250061},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.12465322017669678},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07044234871864319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.221","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.221","pdf_url":"https://aclanthology.org/2025.findings-acl.221.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.221","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.221","pdf_url":"https://aclanthology.org/2025.findings-acl.221.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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888757.pdf","grobid_xml":"https://content.openalex.org/works/W4412888757.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2117748264","https://openalex.org/W4298190863","https://openalex.org/W2518229301","https://openalex.org/W2597205018","https://openalex.org/W2554072523","https://openalex.org/W1671671741","https://openalex.org/W2952002823","https://openalex.org/W2013329450","https://openalex.org/W3104909087","https://openalex.org/W2512421151"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,58,107,157,200],"novel":[3],"scaling":[4,30,90,153],"law":[5],"for":[6,65,203],"generalpurpose":[7],"decoder-only":[8],"language":[9,37,53,67,171],"models":[10,165,183,189],"(LMs)":[11],"trained":[12],"on":[13,102,166],"multilingual":[14,23,29,89,204],"data,":[15],"tackling":[16],"the":[17,32,47,61,82,86,93,131,137,146,176],"problem":[18],"of":[19,34,78,88,100,130,150,194],"balancing":[20],"languages":[21,51,80,168],"during":[22],"pretraining.A":[24],"primary":[25],"challenge":[26],"in":[27,81],"studying":[28],"is":[31,69],"difficulty":[33],"analyzing":[35],"individual":[36,50],"performance":[38,112,126],"due":[39],"to":[40,52,96,124,188],"cross-lingual":[41],"transfer.To":[42],"tackle":[43],"this,":[44],"we":[45,105,155],"shift":[46],"focus":[48],"from":[49,181],"families.We":[54],"introduce":[55],"and":[56,91,118,135,148],"validate":[57],"hypothesis":[59],"that":[60,110,175,190],"test":[62],"cross-entropy":[63],"loss":[64],"each":[66],"family":[68],"determined":[70],"solely":[71],"by":[72],"its":[73],"own":[74],"sampling":[75,119,139,178],"ratio,":[76],"independent":[77],"other":[79],"mixture.This":[83],"insight":[84],"simplifies":[85],"complexity":[87],"make":[92],"analysis":[94],"scalable":[95],"an":[97],"arbitrary":[98],"number":[99],"languages.Building":[101],"this":[103],"hypothesis,":[104],"derive":[106,136],"power-law":[108],"relationship":[109,121],"links":[111],"with":[113],"dataset":[114],"size,":[115],"model":[116,143],"size":[117],"ratios.This":[120],"enables":[122],"us":[123],"predict":[125],"across":[127],"various":[128],"combinations":[129],"above":[132],"three":[133],"quantities,":[134],"optimal":[138,177],"ratios":[140,179],"at":[141,207],"different":[142],"scales.To":[144],"demonstrate":[145],"effectiveness":[147],"accuracy":[149],"our":[151],"proposed":[152],"law,":[154],"perform":[156],"large-scale":[158],"empirical":[159],"study,":[160],"training":[161,206],"more":[162],"than":[163],"100":[164],"23":[167],"spanning":[169],"5":[170],"families.Our":[172],"experiments":[173],"show":[174],"derived":[180],"small":[182],"(85M":[184],"parameters)":[185],"generalize":[186],"effectively":[187],"are":[191],"several":[192],"orders":[193],"magnitude":[195],"larger":[196],"(1.2B":[197],"parameters),":[198],"offering":[199],"resource-efficient":[201],"approach":[202],"LM":[205],"scale.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}