@inproceedings{mohamed-etal-2026-lost,
title = "Lost in the Mix: Evaluating {LLM} Understanding of Code-Switched Text",
author = "Mohamed, Amr and
Zhang, Yang and
Vazirgiannis, Michalis and
Shang, Guokan",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.2080/",
doi = "10.18653/v1/2026.acl-long.2080",
pages = "44922--44938",
ISBN = "979-8-89176-390-6",
abstract = "Code-switching (CSW) is the act of alternating between two or more languages within a single discourse. This phenomenon is widespread in multilingual communities and increasingly prevalent online, exposing large language models (LLMs) to mixed-language inputs. We present a systematic evaluation of LLM *comprehension* under code-switching by generating linguistically grounded CSW variants of established benchmarks (Belebele, MMLU, XNLI) across five typologically diverse languages. Our contributions are: (i) a controlled pipeline for producing CSW test sets that respect linguistic constraints on code-switching; (ii) a multi-model, multi-language analysis showing that inserting non-English tokens into English consistently reduces accuracy on comprehension and reasoning benchmarks, whereas embedding English into non-English contexts often improves it; and (iii) a mitigation study contrasting in-context learning (ICL) with fine-tuning. Across model families, ICL cues yield inconsistent, and sometimes negative, effects, while fine-tuning on CSW data provides modest but reliable gains, partially recovering accuracy under CSW."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohamed-etal-2026-lost">
<titleInfo>
<title>Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michalis</namePart>
<namePart type="family">Vazirgiannis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guokan</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Code-switching (CSW) is the act of alternating between two or more languages within a single discourse. This phenomenon is widespread in multilingual communities and increasingly prevalent online, exposing large language models (LLMs) to mixed-language inputs. We present a systematic evaluation of LLM *comprehension* under code-switching by generating linguistically grounded CSW variants of established benchmarks (Belebele, MMLU, XNLI) across five typologically diverse languages. Our contributions are: (i) a controlled pipeline for producing CSW test sets that respect linguistic constraints on code-switching; (ii) a multi-model, multi-language analysis showing that inserting non-English tokens into English consistently reduces accuracy on comprehension and reasoning benchmarks, whereas embedding English into non-English contexts often improves it; and (iii) a mitigation study contrasting in-context learning (ICL) with fine-tuning. Across model families, ICL cues yield inconsistent, and sometimes negative, effects, while fine-tuning on CSW data provides modest but reliable gains, partially recovering accuracy under CSW.</abstract>
<identifier type="citekey">mohamed-etal-2026-lost</identifier>
<identifier type="doi">10.18653/v1/2026.acl-long.2080</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.2080/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>44922</start>
<end>44938</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text
%A Mohamed, Amr
%A Zhang, Yang
%A Vazirgiannis, Michalis
%A Shang, Guokan
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F mohamed-etal-2026-lost
%X Code-switching (CSW) is the act of alternating between two or more languages within a single discourse. This phenomenon is widespread in multilingual communities and increasingly prevalent online, exposing large language models (LLMs) to mixed-language inputs. We present a systematic evaluation of LLM *comprehension* under code-switching by generating linguistically grounded CSW variants of established benchmarks (Belebele, MMLU, XNLI) across five typologically diverse languages. Our contributions are: (i) a controlled pipeline for producing CSW test sets that respect linguistic constraints on code-switching; (ii) a multi-model, multi-language analysis showing that inserting non-English tokens into English consistently reduces accuracy on comprehension and reasoning benchmarks, whereas embedding English into non-English contexts often improves it; and (iii) a mitigation study contrasting in-context learning (ICL) with fine-tuning. Across model families, ICL cues yield inconsistent, and sometimes negative, effects, while fine-tuning on CSW data provides modest but reliable gains, partially recovering accuracy under CSW.
%R 10.18653/v1/2026.acl-long.2080
%U https://aclanthology.org/2026.acl-long.2080/
%U https://doi.org/10.18653/v1/2026.acl-long.2080
%P 44922-44938
Markdown (Informal)
[Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text](https://aclanthology.org/2026.acl-long.2080/) (Mohamed et al., ACL 2026)
ACL
- Amr Mohamed, Yang Zhang, Michalis Vazirgiannis, and Guokan Shang. 2026. Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 44922–44938, San Diego, California, United States. Association for Computational Linguistics.