@inproceedings{aggarwal-etal-2024-maple,
title = "{MAPLE}: Multilingual Evaluation of Parameter Efficient Finetuning of Large Language Models",
author = "Aggarwal, Divyanshu and
Sathe, Ashutosh and
Watts, Ishaan and
Sitaram, Sunayana",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.881/",
doi = "10.18653/v1/2024.findings-acl.881",
pages = "14824--14867",
abstract = "Parameter efficient finetuning has emerged as a viable solution for improving the performance of Large Language Models without requiring massive resources and compute. Prior work on multilingual evaluation has shown that there is a large gap between the performance of LLMs on English and other languages. Further, there is also a large gap between the performance of smaller open-source models and larger LLMs. Finetuning can be an effective way to bridge this gap and make language models more equitable. In this work, we finetune the Llama-2 and Mistral models on two synthetic multilingual instruction tuning datasets to determine its effect on model performance on six downstream tasks covering forty one languages in all. Additionally, we experiment with various parameters, such as rank for low-rank adaptation and values of quantisation to determine their effects on downstream performance and find that higher rank and higher quantisation values benefit low-resource languages. We find that parameter efficient finetuning of smaller open-source models sometimes bridges the gap between the performance of these models and the larger ones, however, English performance can take a hit. We also find that finetuning sometimes improves performance on low-resource languages, while degrading performance on high-resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aggarwal-etal-2024-maple">
<titleInfo>
<title>MAPLE: Multilingual Evaluation of Parameter Efficient Finetuning of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Divyanshu</namePart>
<namePart type="family">Aggarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Sathe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ishaan</namePart>
<namePart type="family">Watts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Parameter efficient finetuning has emerged as a viable solution for improving the performance of Large Language Models without requiring massive resources and compute. Prior work on multilingual evaluation has shown that there is a large gap between the performance of LLMs on English and other languages. Further, there is also a large gap between the performance of smaller open-source models and larger LLMs. Finetuning can be an effective way to bridge this gap and make language models more equitable. In this work, we finetune the Llama-2 and Mistral models on two synthetic multilingual instruction tuning datasets to determine its effect on model performance on six downstream tasks covering forty one languages in all. Additionally, we experiment with various parameters, such as rank for low-rank adaptation and values of quantisation to determine their effects on downstream performance and find that higher rank and higher quantisation values benefit low-resource languages. We find that parameter efficient finetuning of smaller open-source models sometimes bridges the gap between the performance of these models and the larger ones, however, English performance can take a hit. We also find that finetuning sometimes improves performance on low-resource languages, while degrading performance on high-resource languages.</abstract>
<identifier type="citekey">aggarwal-etal-2024-maple</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.881</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.881/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>14824</start>
<end>14867</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MAPLE: Multilingual Evaluation of Parameter Efficient Finetuning of Large Language Models
%A Aggarwal, Divyanshu
%A Sathe, Ashutosh
%A Watts, Ishaan
%A Sitaram, Sunayana
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F aggarwal-etal-2024-maple
%X Parameter efficient finetuning has emerged as a viable solution for improving the performance of Large Language Models without requiring massive resources and compute. Prior work on multilingual evaluation has shown that there is a large gap between the performance of LLMs on English and other languages. Further, there is also a large gap between the performance of smaller open-source models and larger LLMs. Finetuning can be an effective way to bridge this gap and make language models more equitable. In this work, we finetune the Llama-2 and Mistral models on two synthetic multilingual instruction tuning datasets to determine its effect on model performance on six downstream tasks covering forty one languages in all. Additionally, we experiment with various parameters, such as rank for low-rank adaptation and values of quantisation to determine their effects on downstream performance and find that higher rank and higher quantisation values benefit low-resource languages. We find that parameter efficient finetuning of smaller open-source models sometimes bridges the gap between the performance of these models and the larger ones, however, English performance can take a hit. We also find that finetuning sometimes improves performance on low-resource languages, while degrading performance on high-resource languages.
%R 10.18653/v1/2024.findings-acl.881
%U https://aclanthology.org/2024.findings-acl.881/
%U https://doi.org/10.18653/v1/2024.findings-acl.881
%P 14824-14867
Markdown (Informal)
[MAPLE: Multilingual Evaluation of Parameter Efficient Finetuning of Large Language Models](https://aclanthology.org/2024.findings-acl.881/) (Aggarwal et al., Findings 2024)
ACL