@inproceedings{kim-etal-2024-pruning,
title = "Pruning Multilingual Large Language Models for Multilingual Inference",
author = "Kim, Hwichan and
Suzuki, Jun and
Hirasawa, Tosho and
Komachi, Mamoru",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.580",
doi = "10.18653/v1/2024.findings-emnlp.580",
pages = "9921--9942",
abstract = "Multilingual large language models (MLLMs), trained on multilingual balanced data, demonstrate better zero-shot learning performance in non-English languages compared to large language models trained on English-dominant data. However, the disparity in performance between English and non-English languages remains a challenge yet to be fully addressed. This study introduces a promising direction for enhancing non-English performance through a specialized pruning approach. Specifically, we prune MLLMs using bilingual sentence pairs from English and other languages and empirically demonstrate that this pruning strategy can enhance the MLLMs{'} performance in non-English language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2024-pruning">
<titleInfo>
<title>Pruning Multilingual Large Language Models for Multilingual Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hwichan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tosho</namePart>
<namePart type="family">Hirasawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual large language models (MLLMs), trained on multilingual balanced data, demonstrate better zero-shot learning performance in non-English languages compared to large language models trained on English-dominant data. However, the disparity in performance between English and non-English languages remains a challenge yet to be fully addressed. This study introduces a promising direction for enhancing non-English performance through a specialized pruning approach. Specifically, we prune MLLMs using bilingual sentence pairs from English and other languages and empirically demonstrate that this pruning strategy can enhance the MLLMs’ performance in non-English language.</abstract>
<identifier type="citekey">kim-etal-2024-pruning</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.580</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.580</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>9921</start>
<end>9942</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pruning Multilingual Large Language Models for Multilingual Inference
%A Kim, Hwichan
%A Suzuki, Jun
%A Hirasawa, Tosho
%A Komachi, Mamoru
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F kim-etal-2024-pruning
%X Multilingual large language models (MLLMs), trained on multilingual balanced data, demonstrate better zero-shot learning performance in non-English languages compared to large language models trained on English-dominant data. However, the disparity in performance between English and non-English languages remains a challenge yet to be fully addressed. This study introduces a promising direction for enhancing non-English performance through a specialized pruning approach. Specifically, we prune MLLMs using bilingual sentence pairs from English and other languages and empirically demonstrate that this pruning strategy can enhance the MLLMs’ performance in non-English language.
%R 10.18653/v1/2024.findings-emnlp.580
%U https://aclanthology.org/2024.findings-emnlp.580
%U https://doi.org/10.18653/v1/2024.findings-emnlp.580
%P 9921-9942
Markdown (Informal)
[Pruning Multilingual Large Language Models for Multilingual Inference](https://aclanthology.org/2024.findings-emnlp.580) (Kim et al., Findings 2024)
ACL