<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tanwar-etal-2023-multilingual">
    <titleInfo>
        <title>Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Eshaan</namePart>
        <namePart type="family">Tanwar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Subhabrata</namePart>
        <namePart type="family">Dutta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Manish</namePart>
        <namePart type="family">Borthakur</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tanmoy</namePart>
        <namePart type="family">Chakraborty</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In-context learning (ICL) unfolds as large language models become capable of inferring test labels conditioned on a few labeled samples without any gradient update. ICL-enabled large language models provide a promising step forward toward bypassing recurrent annotation costs in a low-resource setting. Yet, only a handful of past studies have explored ICL in a cross-lingual setting, in which the need for transferring label-knowledge from a high-resource language to a low-resource one is immensely crucial. To bridge the gap, we provide the first in-depth analysis of ICL for cross-lingual text classification. We find that the prevalent mode of selecting random input-label pairs to construct the prompt-context is severely limited in the case of cross-lingual ICL, primarily due to the lack of alignment in the input as well as the output spaces. To mitigate this, we propose a novel prompt construction strategy — Cross-lingual In-context Source Target Alignment (X-InSTA). With an injected coherence in the semantics of the input examples and a task-based alignment across the source and target languages, X-InSTA is able to outperform random prompt selection by a large margin across three different tasks using 44 different cross-lingual pairs.</abstract>
    <identifier type="citekey">tanwar-etal-2023-multilingual</identifier>
    <identifier type="doi">10.18653/v1/2023.acl-long.346</identifier>
    <location>
        <url>https://aclanthology.org/2023.acl-long.346</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>6292</start>
            <end>6307</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment
%A Tanwar, Eshaan
%A Dutta, Subhabrata
%A Borthakur, Manish
%A Chakraborty, Tanmoy
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F tanwar-etal-2023-multilingual
%X In-context learning (ICL) unfolds as large language models become capable of inferring test labels conditioned on a few labeled samples without any gradient update. ICL-enabled large language models provide a promising step forward toward bypassing recurrent annotation costs in a low-resource setting. Yet, only a handful of past studies have explored ICL in a cross-lingual setting, in which the need for transferring label-knowledge from a high-resource language to a low-resource one is immensely crucial. To bridge the gap, we provide the first in-depth analysis of ICL for cross-lingual text classification. We find that the prevalent mode of selecting random input-label pairs to construct the prompt-context is severely limited in the case of cross-lingual ICL, primarily due to the lack of alignment in the input as well as the output spaces. To mitigate this, we propose a novel prompt construction strategy — Cross-lingual In-context Source Target Alignment (X-InSTA). With an injected coherence in the semantics of the input examples and a task-based alignment across the source and target languages, X-InSTA is able to outperform random prompt selection by a large margin across three different tasks using 44 different cross-lingual pairs.
%R 10.18653/v1/2023.acl-long.346
%U https://aclanthology.org/2023.acl-long.346
%U https://doi.org/10.18653/v1/2023.acl-long.346
%P 6292-6307

Markdown (Informal)

[Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment](https://aclanthology.org/2023.acl-long.346) (Tanwar et al., ACL 2023)

• Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment (Tanwar et al., ACL 2023)

ACL

• Eshaan Tanwar, Subhabrata Dutta, Manish Borthakur, and Tanmoy Chakraborty. 2023. Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6292–6307, Toronto, Canada. Association for Computational Linguistics.