@inproceedings{zhang-etal-2023-multilingual,
title = "Multilingual Large Language Models Are Not (Yet) Code-Switchers",
author = "Zhang, Ruochen and
Cahyawijaya, Samuel and
Cruz, Jan Christian Blaise and
Winata, Genta and
Aji, Alham",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.774",
doi = "10.18653/v1/2023.emnlp-main.774",
pages = "12567--12582",
abstract = "Multilingual Large Language Models (LLMs) have recently shown great capabilities in a wide range of tasks, exhibiting state-of-the-art performance through zero-shot or few-shot prompting methods. While there have been extensive studies on their abilities in monolingual tasks, the investigation of their potential in the context of code-switching (CSW), the practice of alternating languages within an utterance, remains relatively uncharted. In this paper, we provide a comprehensive empirical analysis of various multilingual LLMs, benchmarking their performance across four tasks: sentiment analysis, machine translation, summarization and word-level language identification. Our results indicate that despite multilingual LLMs exhibiting promising outcomes in certain tasks using zero or few-shot prompting, they still underperform in comparison to fine-tuned models of much smaller scales. We argue that current {``}multilingualism{'} in LLMs does not inherently imply proficiency with code-switching texts, calling for future research to bridge this discrepancy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-multilingual">
<titleInfo>
<title>Multilingual Large Language Models Are Not (Yet) Code-Switchers</title>
</titleInfo>
<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">Samuel</namePart>
<namePart type="family">Cahyawijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="given">Christian</namePart>
<namePart type="given">Blaise</namePart>
<namePart type="family">Cruz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alham</namePart>
<namePart type="family">Aji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual Large Language Models (LLMs) have recently shown great capabilities in a wide range of tasks, exhibiting state-of-the-art performance through zero-shot or few-shot prompting methods. While there have been extensive studies on their abilities in monolingual tasks, the investigation of their potential in the context of code-switching (CSW), the practice of alternating languages within an utterance, remains relatively uncharted. In this paper, we provide a comprehensive empirical analysis of various multilingual LLMs, benchmarking their performance across four tasks: sentiment analysis, machine translation, summarization and word-level language identification. Our results indicate that despite multilingual LLMs exhibiting promising outcomes in certain tasks using zero or few-shot prompting, they still underperform in comparison to fine-tuned models of much smaller scales. We argue that current “multilingualism’ in LLMs does not inherently imply proficiency with code-switching texts, calling for future research to bridge this discrepancy.</abstract>
<identifier type="citekey">zhang-etal-2023-multilingual</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.774</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.774</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>12567</start>
<end>12582</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Large Language Models Are Not (Yet) Code-Switchers
%A Zhang, Ruochen
%A Cahyawijaya, Samuel
%A Cruz, Jan Christian Blaise
%A Winata, Genta
%A Aji, Alham
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhang-etal-2023-multilingual
%X Multilingual Large Language Models (LLMs) have recently shown great capabilities in a wide range of tasks, exhibiting state-of-the-art performance through zero-shot or few-shot prompting methods. While there have been extensive studies on their abilities in monolingual tasks, the investigation of their potential in the context of code-switching (CSW), the practice of alternating languages within an utterance, remains relatively uncharted. In this paper, we provide a comprehensive empirical analysis of various multilingual LLMs, benchmarking their performance across four tasks: sentiment analysis, machine translation, summarization and word-level language identification. Our results indicate that despite multilingual LLMs exhibiting promising outcomes in certain tasks using zero or few-shot prompting, they still underperform in comparison to fine-tuned models of much smaller scales. We argue that current “multilingualism’ in LLMs does not inherently imply proficiency with code-switching texts, calling for future research to bridge this discrepancy.
%R 10.18653/v1/2023.emnlp-main.774
%U https://aclanthology.org/2023.emnlp-main.774
%U https://doi.org/10.18653/v1/2023.emnlp-main.774
%P 12567-12582
Markdown (Informal)
[Multilingual Large Language Models Are Not (Yet) Code-Switchers](https://aclanthology.org/2023.emnlp-main.774) (Zhang et al., EMNLP 2023)
ACL
- Ruochen Zhang, Samuel Cahyawijaya, Jan Christian Blaise Cruz, Genta Winata, and Alham Aji. 2023. Multilingual Large Language Models Are Not (Yet) Code-Switchers. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12567–12582, Singapore. Association for Computational Linguistics.