<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2024-representational">
    <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>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>In this paper, we investigate the capability of Large Language Models (LLMs) to represent texts in multilingual contexts. Our findings show that sentence representations derived from LLMs exhibit a high degree of isomorphism across languages.This existing isomorphism can facilitate representational alignments in zero-shot and few-shot settings.Specifically, by applying a contrastive objective at the representation level with only a small number of translation pairs (e.g., 100), we substantially improve models’ performance on Semantic Textual Similarity (STS) tasks across languages. This representation-level approach proves to be more efficient and effective for semantic alignment than continued pretraining or instruction tuning. Interestingly, we also observe substantial STS improvements within individual languages, even without a monolingual objective specifically designed for this purpose.</abstract>
    <identifier type="citekey">wu-etal-2024-representational</identifier>
    <identifier type="doi">10.18653/v1/2024.findings-emnlp.823</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-emnlp.823/</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>14074</start>
            <end>14085</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 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 wu-etal-2024-representational
%X In this paper, we investigate the capability of Large Language Models (LLMs) to represent texts in multilingual contexts. Our findings show that sentence representations derived from LLMs exhibit a high degree of isomorphism across languages.This existing isomorphism can facilitate representational alignments in zero-shot and few-shot settings.Specifically, by applying a contrastive objective at the representation level with only a small number of translation pairs (e.g., 100), we substantially improve models’ performance on Semantic Textual Similarity (STS) tasks across languages. This representation-level approach proves to be more efficient and effective for semantic alignment than continued pretraining or instruction tuning. Interestingly, we also observe substantial STS improvements within individual languages, even without a monolingual objective specifically designed for this purpose.
%R 10.18653/v1/2024.findings-emnlp.823
%U https://aclanthology.org/2024.findings-emnlp.823/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.823
%P 14074-14085

Markdown (Informal)

[Representational Isomorphism and Alignment of Multilingual Large Language Models](https://aclanthology.org/2024.findings-emnlp.823/) (Wu et al., Findings 2024)

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

ACL

• Di Wu, Yibin Lei, Andrew Yates, and Christof Monz. 2024. Representational Isomorphism and Alignment of Multilingual Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 14074–14085, Miami, Florida, USA. Association for Computational Linguistics.