<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-monolingual">
    <titleInfo>
        <title>Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pinzhen</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shaoxiong</namePart>
        <namePart type="family">Ji</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nikolay</namePart>
        <namePart type="family">Bogoychev</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrey</namePart>
        <namePart type="family">Kutuzov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Barry</namePart>
        <namePart type="family">Haddow</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kenneth</namePart>
        <namePart type="family">Heafield</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yvette</namePart>
            <namePart type="family">Graham</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Matthew</namePart>
            <namePart type="family">Purver</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">St. Julian’s, Malta</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. While such efforts are often carried out in a single language, we empirically analyze cost-efficient strategies for multilingual scenarios. Our study employs the Alpaca dataset and machine translations of it to form multilingual data, which is then used to tune LLMs through either low-rank adaptation or full-parameter training. Under a controlled computation budget, comparisons show that multilingual tuning is on par or better than tuning a model for each language. Furthermore, multilingual tuning with downsampled data can be as powerful and more robust. Our findings serve as a guide for expanding language support through instruction tuning.</abstract>
    <identifier type="citekey">chen-etal-2024-monolingual</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-eacl.90</url>
    </location>
    <part>
        <date>2024-03</date>
        <extent unit="page">
            <start>1347</start>
            <end>1356</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca
%A Chen, Pinzhen
%A Ji, Shaoxiong
%A Bogoychev, Nikolay
%A Kutuzov, Andrey
%A Haddow, Barry
%A Heafield, Kenneth
%Y Graham, Yvette
%Y Purver, Matthew
%S Findings of the Association for Computational Linguistics: EACL 2024
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F chen-etal-2024-monolingual
%X Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. While such efforts are often carried out in a single language, we empirically analyze cost-efficient strategies for multilingual scenarios. Our study employs the Alpaca dataset and machine translations of it to form multilingual data, which is then used to tune LLMs through either low-rank adaptation or full-parameter training. Under a controlled computation budget, comparisons show that multilingual tuning is on par or better than tuning a model for each language. Furthermore, multilingual tuning with downsampled data can be as powerful and more robust. Our findings serve as a guide for expanding language support through instruction tuning.
%U https://aclanthology.org/2024.findings-eacl.90
%P 1347-1356

Markdown (Informal)

[Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca](https://aclanthology.org/2024.findings-eacl.90) (Chen et al., Findings 2024)

• Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca (Chen et al., Findings 2024)

ACL

• Pinzhen Chen, Shaoxiong Ji, Nikolay Bogoychev, Andrey Kutuzov, Barry Haddow, and Kenneth Heafield. 2024. Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca. In Findings of the Association for Computational Linguistics: EACL 2024, pages 1347–1356, St. Julian’s, Malta. Association for Computational Linguistics.