{"id":"https://openalex.org/W4401042060","doi":"https://doi.org/10.18653/v1/2024.vardial-1.2","title":"What Drives Performance in Multilingual Language Models?","display_name":"What Drives Performance in Multilingual Language Models?","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401042060","doi":"https://doi.org/10.18653/v1/2024.vardial-1.2"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.vardial-1.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.vardial-1.2","pdf_url":"https://aclanthology.org/2024.vardial-1.2.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 Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.vardial-1.2.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044980518","display_name":"Sina Bagheri Nezhad","orcid":"https://orcid.org/0000-0002-7863-8739"},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sina Bagheri Nezhad","raw_affiliation_strings":["Portland State University"],"affiliations":[{"raw_affiliation_string":"Portland State University","institution_ids":["https://openalex.org/I126345244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112206342","display_name":"Ameeta Agrawal","orcid":"https://orcid.org/0000-0001-6189-099X"},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ameeta Agrawal","raw_affiliation_strings":["Portland State University"],"affiliations":[{"raw_affiliation_string":"Portland State University","institution_ids":["https://openalex.org/I126345244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044980518"],"corresponding_institution_ids":["https://openalex.org/I126345244"],"apc_list":null,"apc_paid":null,"fwci":1.0034,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79825996,"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":"16","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7815999984741211,"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":0.7815999984741211,"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":0.7443000078201294,"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":0.7430567741394043},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40008285641670227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430567741394043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40008285641670227}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.vardial-1.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.vardial-1.2","pdf_url":"https://aclanthology.org/2024.vardial-1.2.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 Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.vardial-1.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.vardial-1.2","pdf_url":"https://aclanthology.org/2024.vardial-1.2.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 Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401042060.pdf","grobid_xml":"https://content.openalex.org/works/W4401042060.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"This":[0],"study":[1,17],"investigates":[2],"the":[3,6,30,50,62,71,99,118,132,142,153],"factors":[4,74],"influencing":[5],"performance":[7],"of":[8,73,120,146,155],"multilingual":[9,160],"large":[10],"language":[11,22,83,110],"models":[12],"(MLLMs)":[13],"across":[14],"diverse":[15],"languages.We":[16],"6":[18],"MLLMs,":[19],"including":[20],"masked":[21],"models,":[23,25],"autoregressive":[24],"and":[26,54,85,109,126,144,149,158],"instruction-tuned":[27],"LLMs,":[28],"on":[29,88],"SIB-200":[31],"dataset,":[32],"a":[33],"topic":[34],"classification":[35],"dataset":[36],"encompassing":[37],"204":[38],"languages.Our":[39],"analysis":[40,92],"considers":[41],"three":[42],"scenarios:":[43],"ALL":[44],"languages,":[45,116],"SEEN":[46,104],"languages":[47,56],"(present":[48],"in":[49,61,66],"model's":[51,63],"pretraining":[52,64,77,95],"data),":[53],"UNSEEN":[55,115],"(not":[57],"present":[58],"or":[59],"documented":[60],"data":[65,78,96],"any":[67],"meaningful":[68],"way).We":[69],"examine":[70],"impact":[72],"such":[75],"as":[76],"size,":[79],"general":[80],"resource":[81],"availability,":[82],"family,":[84],"script":[86,107],"type":[87,108],"model":[89,124],"performance.Decision":[90],"tree":[91],"reveals":[93],"that":[94],"size":[97,125],"is":[98],"most":[100,133],"influential":[101],"factor":[102],"for":[103,114],"languages.However,":[105],"interestingly,":[106],"family":[111],"are":[112],"crucial":[113],"highlighting":[117],"importance":[119],"crosslingual":[121],"transfer":[122],"learning.Notably,":[123],"architecture":[127],"do":[128],"not":[129],"significantly":[130],"alter":[131],"important":[134],"features":[135],"identified.Our":[136],"findings":[137],"provide":[138],"valuable":[139],"insights":[140],"into":[141],"strengths":[143],"limitations":[145],"current":[147],"MLLMs":[148],"hope":[150],"to":[151],"guide":[152],"development":[154],"more":[156],"effective":[157],"equitable":[159],"NLP":[161],"systems.":[162],"1":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}