{"id":"https://openalex.org/W4416034205","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1153","title":"False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models","display_name":"False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034205","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1153"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1153","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1153","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1153.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: EMNLP 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-emnlp.1153.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019317146","display_name":"Julie Kallini","orcid":"https://orcid.org/0000-0003-0835-6485"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julie Kallini","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087088138","display_name":"Dan Jurafsky","orcid":"https://orcid.org/0000-0002-6459-7745"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Jurafsky","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042601761","display_name":"Christopher Potts","orcid":"https://orcid.org/0000-0002-7978-6055"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Potts","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033914946","display_name":"Martijn Bartelds","orcid":"https://orcid.org/0000-0003-1006-8669"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martijn Bartelds","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"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":"21138","last_page":"21154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.13369999825954437,"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":0.13369999825954437,"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/T12090","display_name":"Language and cultural evolution","score":0.1273999959230423,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.09459999948740005,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5569000244140625},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3723999857902527},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.36070001125335693},{"id":"https://openalex.org/keywords/multilingualism","display_name":"Multilingualism","score":0.2989000082015991},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.29429998993873596},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.2777000069618225}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.6096000075340271},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5569000244140625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5213000178337097},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5164999961853027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4284000098705292},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4065000116825104},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1153","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1153","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1153.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1153","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1153","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1153.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2289860940","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"2146755","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6141350605","display_name":null,"funder_award_id":"DGE-2146755","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034205.pdf","grobid_xml":"https://content.openalex.org/works/W4416034205.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Subword":[0],"tokenizers":[1],"trained":[2],"on":[3,56],"multilingual":[4,149,163],"corpora":[5],"naturally":[6],"produce":[7],"overlapping":[8],"tokens":[9,81],"across":[10,83],"languages.Does":[11],"token":[12,36,146],"overlap":[13,64,74,94,125,138,147],"facilitate":[14],"cross-lingual":[15,103],"transfer":[16,133],"or":[17,38],"instead":[18],"introduce":[19],"interference":[20],"between":[21],"languages?Prior":[22],"work":[23],"offers":[24],"mixed":[25],"evidence,":[26],"partly":[27],"due":[28],"to":[29,71],"varied":[30,62],"setups":[31],"and":[32,91,118,131,151],"confounders,":[33],"such":[34],"as":[35,137],"frequency":[37],"subword":[39],"segmentation":[40],"granularity.To":[41],"address":[42],"this":[43,107],"question,":[44],"we":[45,51,66,120],"devise":[46],"a":[47,68,158],"controlled":[48],"experiment":[49],"where":[50],"train":[52],"bilingual":[53],"autoregressive":[54],"models":[55,113,123,127,150],"multiple":[57],"language":[58],"pairs":[59],"under":[60],"systematically":[61],"vocabulary":[63,156],"settings.Crucially,":[65],"explore":[67],"new":[69],"dimension":[70],"understanding":[72],"how":[73],"affects":[75],"transfer:":[76],"the":[77,143],"semantic":[78,104],"similarity":[79],"of":[80,95,145],"shared":[82,155],"languages.We":[84],"first":[85],"analyze":[86],"our":[87,140],"models'":[88],"hidden":[89],"representations":[90],"find":[92,121],"that":[93,101,122,132,153],"any":[96],"kind":[97],"creates":[98],"embedding":[99],"spaces":[100],"capture":[102],"relationships,":[105],"while":[106],"effect":[108],"is":[109],"much":[110],"weaker":[111],"in":[112,148],"with":[114,124,128],"disjoint":[115,129],"vocabularies.On":[116],"XNLI":[117],"XQuAD,":[119],"outperform":[126],"vocabularies,":[130],"performance":[134],"generally":[135],"improves":[136],"increases.Overall,":[139],"findings":[141],"highlight":[142],"advantages":[144],"show":[152],"substantial":[154],"remains":[157],"beneficial":[159],"design":[160],"choice":[161],"for":[162],"tokenizers.https://github.com/jkallini/":[164],"false-friends":[165],"Full":[166],"OverlapHigh-sim":[167]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}