@inproceedings{yoo-etal-2026-code,
title = "Code-Switching for Multilingual {LLM}s",
author = "Yoo, Haneul and
Oh, Juhyun and
Winata, Genta Indra and
Zhang, Ruochen and
Solorio, Thamar and
Oh, Alice",
editor = "Okazaki, Naoaki and
Wang, Zhongqing",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics: Tutorial Abstracts",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-tutorials.1/",
pages = "1--10",
ISBN = "979-8-89176-443-9",
abstract = "This tutorial provides a structured overview of code-switching for multilingual large language models (LLMs), connecting linguistic theory, NLP methodology, and human-centered perspectives. Code-switching is a natural communicative practice among multilingual speakers and is increasingly central to LLM interactions, where users bring mixed-language practices to prompts and models themselves may produce mixed-language outputs. The tutorial will cover theoretical foundations from sociolinguistics, code-switching behavior in human-AI interaction, datasets and evaluation benchmarks, synthetic data generation, multilingual LLM training and inference, mechanistic interpretability of unintended language switching, speech and multimodal code-switching, and societal impacts. By synthesizing work across NLP, linguistics, HCI, speech processing, and multilingual communities, the tutorial aims to give participants a coherent view of the field and identify open challenges for building multilingual LLMs that better reflect how multilingual users actually communicate."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yoo-etal-2026-code">
<titleInfo>
<title>Code-Switching for Multilingual LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haneul</namePart>
<namePart type="family">Yoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juhyun</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruochen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: Tutorial Abstracts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongqing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-443-9</identifier>
</relatedItem>
<abstract>This tutorial provides a structured overview of code-switching for multilingual large language models (LLMs), connecting linguistic theory, NLP methodology, and human-centered perspectives. Code-switching is a natural communicative practice among multilingual speakers and is increasingly central to LLM interactions, where users bring mixed-language practices to prompts and models themselves may produce mixed-language outputs. The tutorial will cover theoretical foundations from sociolinguistics, code-switching behavior in human-AI interaction, datasets and evaluation benchmarks, synthetic data generation, multilingual LLM training and inference, mechanistic interpretability of unintended language switching, speech and multimodal code-switching, and societal impacts. By synthesizing work across NLP, linguistics, HCI, speech processing, and multilingual communities, the tutorial aims to give participants a coherent view of the field and identify open challenges for building multilingual LLMs that better reflect how multilingual users actually communicate.</abstract>
<identifier type="citekey">yoo-etal-2026-code</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-tutorials.1/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Code-Switching for Multilingual LLMs
%A Yoo, Haneul
%A Oh, Juhyun
%A Winata, Genta Indra
%A Zhang, Ruochen
%A Solorio, Thamar
%A Oh, Alice
%Y Okazaki, Naoaki
%Y Wang, Zhongqing
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: Tutorial Abstracts
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-443-9
%F yoo-etal-2026-code
%X This tutorial provides a structured overview of code-switching for multilingual large language models (LLMs), connecting linguistic theory, NLP methodology, and human-centered perspectives. Code-switching is a natural communicative practice among multilingual speakers and is increasingly central to LLM interactions, where users bring mixed-language practices to prompts and models themselves may produce mixed-language outputs. The tutorial will cover theoretical foundations from sociolinguistics, code-switching behavior in human-AI interaction, datasets and evaluation benchmarks, synthetic data generation, multilingual LLM training and inference, mechanistic interpretability of unintended language switching, speech and multimodal code-switching, and societal impacts. By synthesizing work across NLP, linguistics, HCI, speech processing, and multilingual communities, the tutorial aims to give participants a coherent view of the field and identify open challenges for building multilingual LLMs that better reflect how multilingual users actually communicate.
%U https://aclanthology.org/2026.aacl-tutorials.1/
%P 1-10
Markdown (Informal)
[Code-Switching for Multilingual LLMs](https://aclanthology.org/2026.aacl-tutorials.1/) (Yoo et al., AACL-IJCNLP 2026)
ACL
- Haneul Yoo, Juhyun Oh, Genta Indra Winata, Ruochen Zhang, Thamar Solorio, and Alice Oh. 2026. Code-Switching for Multilingual LLMs. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: Tutorial Abstracts, pages 1–10, Hengqin, China. Association for Computational Linguistics.