<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mela-etal-2024-mass">
    <titleInfo>
        <title>Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Tamayo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aitor</namePart>
        <namePart type="family">Gonzalez-Agirre</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Javier</namePart>
        <namePart type="family">Hernando</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marta</namePart>
        <namePart type="family">Villegas</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>Recent research has explored methods for updating and modifying factual knowledge in large language models, often focusing on specific multi-layer perceptron blocks. This study expands on this work by examining the effectiveness of existing knowledge editing methods across languages and delving into the role of attention mechanisms in this process. Drawing from the insights gained, we propose Mass-Editing Memory with Attention in Transformers (MEMAT), a method that achieves significant improvements in all metrics while requiring minimal parameter modifications. MEMAT delivers a remarkable 10% increase in magnitude metrics, benefits languages not included in the training data and also demonstrates a high degree of portability. Our code and data are at https://github.com/dtamayo-nlp/MEMAT.</abstract>
    <identifier type="citekey">mela-etal-2024-mass</identifier>
    <identifier type="doi">10.18653/v1/2024.findings-acl.347</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-acl.347/</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>5831</start>
            <end>5847</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge
%A Tamayo, Daniel
%A Gonzalez-Agirre, Aitor
%A Hernando, Javier
%A Villegas, Marta
%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 mela-etal-2024-mass
%X Recent research has explored methods for updating and modifying factual knowledge in large language models, often focusing on specific multi-layer perceptron blocks. This study expands on this work by examining the effectiveness of existing knowledge editing methods across languages and delving into the role of attention mechanisms in this process. Drawing from the insights gained, we propose Mass-Editing Memory with Attention in Transformers (MEMAT), a method that achieves significant improvements in all metrics while requiring minimal parameter modifications. MEMAT delivers a remarkable 10% increase in magnitude metrics, benefits languages not included in the training data and also demonstrates a high degree of portability. Our code and data are at https://github.com/dtamayo-nlp/MEMAT.
%R 10.18653/v1/2024.findings-acl.347
%U https://aclanthology.org/2024.findings-acl.347/
%U https://doi.org/10.18653/v1/2024.findings-acl.347
%P 5831-5847

Markdown (Informal)

[Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge](https://aclanthology.org/2024.findings-acl.347/) (Tamayo et al., Findings 2024)

• Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge (Tamayo et al., Findings 2024)

ACL

• Daniel Tamayo, Aitor Gonzalez-Agirre, Javier Hernando, and Marta Villegas. 2024. Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge. In Findings of the Association for Computational Linguistics: ACL 2024, pages 5831–5847, Bangkok, Thailand. Association for Computational Linguistics.