<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2024-representational-isomorphism">
    <titleInfo>
        <title>Representational Isomorphism and Alignment of Multilingual Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Di</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yibin</namePart>
        <namePart type="family">Lei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrew</namePart>
        <namePart type="family">Yates</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christof</namePart>
        <namePart type="family">Monz</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>Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jonne</namePart>
            <namePart type="family">Sälevä</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Abraham</namePart>
            <namePart type="family">Owodunni</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>In this extended abstract, we investigate the capability of Large Language Models (LLMs) to represent texts in multilingual contexts. Our findings reveal that sentence representations derived from LLMs exhibit a high degree of isomorphism across languages. This existing isomorphism facilitates representational alignments in few-shot settings. Specifically, by applying a contrastive objective at the representation level with only a small number (e.g., 100) of translation pairs, we significantly improve models’ performance on Semantic Textual Similarity (STS) tasks across languages.</abstract>
    <identifier type="citekey">wu-etal-2024-representational-isomorphism</identifier>
    <location>
        <url>https://aclanthology.org/2024.mrl-1.24</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>293</start>
            <end>297</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Representational Isomorphism and Alignment of Multilingual Large Language Models
%A Wu, Di
%A Lei, Yibin
%A Yates, Andrew
%A Monz, Christof
%Y Sälevä, Jonne
%Y Owodunni, Abraham
%S Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F wu-etal-2024-representational-isomorphism
%X In this extended abstract, we investigate the capability of Large Language Models (LLMs) to represent texts in multilingual contexts. Our findings reveal that sentence representations derived from LLMs exhibit a high degree of isomorphism across languages. This existing isomorphism facilitates representational alignments in few-shot settings. Specifically, by applying a contrastive objective at the representation level with only a small number (e.g., 100) of translation pairs, we significantly improve models’ performance on Semantic Textual Similarity (STS) tasks across languages.
%U https://aclanthology.org/2024.mrl-1.24
%P 293-297

Markdown (Informal)

[Representational Isomorphism and Alignment of Multilingual Large Language Models](https://aclanthology.org/2024.mrl-1.24) (Wu et al., MRL 2024)

• Representational Isomorphism and Alignment of Multilingual Large Language Models (Wu et al., MRL 2024)

ACL

• Di Wu, Yibin Lei, Andrew Yates, and Christof Monz. 2024. Representational Isomorphism and Alignment of Multilingual Large Language Models. In Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024), pages 293–297, Miami, Florida, USA. Association for Computational Linguistics.