{"id":"https://openalex.org/W4415311358","doi":"https://doi.org/10.18653/v1/2026.acl-long.2080","title":"Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text","display_name":"Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415311358","doi":"https://doi.org/10.18653/v1/2026.acl-long.2080"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.2080","doi":"https://doi.org/10.18653/v1/2026.acl-long.2080","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2080","pdf_url":"https://aclanthology.org/2026.acl-long.2080.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.2080.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021329808","display_name":"Amr Mahmoud Salem Mohamed","orcid":"https://orcid.org/0000-0002-1583-7503","observed_orcids":["https://orcid.org/0000-0002-1583-7503","https://orcid.org/0009-0001-3485-1706"]},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Amr Mohamed","raw_affiliation_strings":["Ecole Polytechnique"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique","institution_ids":["https://openalex.org/I142476485"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["Ecole Polytechnique"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique","institution_ids":["https://openalex.org/I142476485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057695979","display_name":"Michalis Vazirgiannis","orcid":"https://orcid.org/0000-0001-5923-4440","observed_orcids":["https://orcid.org/0000-0001-5923-4440"]},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Michalis Vazirgiannis","raw_affiliation_strings":["Ecole Polytechnique"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique","institution_ids":["https://openalex.org/I142476485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038162261","display_name":"Guokan Shang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guokan Shang","raw_affiliation_strings":["Ecole Polytechnique"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique","institution_ids":["https://openalex.org/I142476485"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142476485"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01106577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"44922","last_page":"44938"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.48899999260902405,"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":0.48899999260902405,"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":0.4666000008583069,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.004999999888241291,"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/code-switching","display_name":"code-switching","score":0.9980000257492065},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9729999899864197},{"id":"https://openalex.org/keywords/mixed-language-text","display_name":"mixed-language text","score":0.5709999799728394},{"id":"https://openalex.org/keywords/test-set-generation","display_name":"test set generation","score":0.6520000100135803},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.8009999990463257},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.9309999942779541},{"id":"https://openalex.org/keywords/reasoning-benchmarks","display_name":"reasoning benchmarks","score":0.47999998927116394},{"id":"https://openalex.org/keywords/multilingual-communities","display_name":"multilingual communities","score":0.4350000023841858}],"concepts":[{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.7439000010490417},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5885000228881836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5806000232696533},{"id":"https://openalex.org/C114010052","wikidata":"https://www.wikidata.org/wiki/Q150352","display_name":"Foreign language","level":2,"score":0.5740000009536743},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5274999737739563},{"id":"https://openalex.org/C50335755","wikidata":"https://www.wikidata.org/wiki/Q483247","display_name":"Phenomenon","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42910000681877136},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3531000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33970001339912415},{"id":"https://openalex.org/C2778780117","wikidata":"https://www.wikidata.org/wiki/Q3269423","display_name":"Reading comprehension","level":3,"score":0.33239999413490295},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C49876356","wikidata":"https://www.wikidata.org/wiki/Q7002651","display_name":"Neuroscience of multilingualism","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C11693617","wikidata":"https://www.wikidata.org/wiki/Q181839","display_name":"Pragmatics","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2711000144481659}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.2080","doi":"https://doi.org/10.18653/v1/2026.acl-long.2080","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2080","pdf_url":"https://aclanthology.org/2026.acl-long.2080.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.14012","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.14012","pdf_url":"https://arxiv.org/pdf/2506.14012","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.14012","doi":"https://doi.org/10.48550/arxiv.2506.14012","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.14012","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.2080","doi":"https://doi.org/10.18653/v1/2026.acl-long.2080","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2080","pdf_url":"https://aclanthology.org/2026.acl-long.2080.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415311358.pdf","grobid_xml":"https://content.openalex.org/works/W4415311358.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7128772843","https://openalex.org/W7123436778","https://openalex.org/W4416392994","https://openalex.org/W7222224986","https://openalex.org/W2884096449","https://openalex.org/W7160196920","https://openalex.org/W4389519244","https://openalex.org/W7104387339","https://openalex.org/W7212397268","https://openalex.org/W4404342393"],"abstract_inverted_index":{"Code-switching":[0],"(CSW)":[1],"is":[2,17],"the":[3],"act":[4],"of":[5,38,49],"alternating":[6],"between":[7],"two":[8],"or":[9],"more":[10],"languages":[11],"within":[12],"a":[13,35,63,78,108],"single":[14],"discourse.This":[15],"phenomenon":[16],"widespread":[18],"in":[19],"multilingual":[20],"communities":[21],"and":[22,94,106,123],"increasingly":[23],"prevalent":[24],"online,":[25],"exposing":[26],"large":[27],"language":[28],"models":[29],"(LLMs)":[30],"to":[31],"mixed-language":[32],"inputs.We":[33],"present":[34],"systematic":[36],"evaluation":[37],"LLM":[39],"comprehension":[40,93],"under":[41,140],"code-switching":[42],"by":[43],"generating":[44],"linguistically":[45],"grounded":[46],"CSW":[47,68,130],"variants":[48],"established":[50],"benchmarks":[51],"(Belebele,":[52],"MMLU,":[53],"XNLI)":[54],"across":[55],"five":[56],"typologically":[57],"diverse":[58],"languages.Our":[59],"contributions":[60],"are:":[61],"(i)":[62],"controlled":[64],"pipeline":[65],"for":[66],"producing":[67],"test":[69],"sets":[70],"that":[71,83],"respect":[72],"linguistic":[73],"constraints":[74],"on":[75,92,129],"code-switching;":[76],"(ii)":[77],"multi-model,":[79],"multi-language":[80],"analysis":[81],"showing":[82],"inserting":[84],"non-English":[85,101],"tokens":[86],"into":[87,100],"English":[88,99],"consistently":[89],"reduces":[90],"accuracy":[91,139],"reasoning":[95],"benchmarks,":[96],"whereas":[97],"embedding":[98],"contexts":[102],"often":[103],"improves":[104],"it;":[105],"(iii)":[107],"mitigation":[109],"study":[110],"contrasting":[111],"in-context":[112],"learning":[113],"(ICL)":[114],"with":[115],"finetuning.Across":[116],"model":[117],"families,":[118],"ICL":[119],"cues":[120],"yield":[121],"inconsistent,":[122],"sometimes":[124],"negative,":[125],"effects,":[126],"while":[127],"fine-tuning":[128],"data":[131],"provides":[132],"modest":[133],"but":[134],"reliable":[135],"gains,":[136],"partially":[137],"recovering":[138],"CSW.":[141]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-18T00:00:00"}