<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="enguehard-2023-sequential">
    <titleInfo>
        <title>Sequential Integrated Gradients: a simple but effective method for explaining language models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Joseph</namePart>
        <namePart type="family">Enguehard</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>Findings of the Association for Computational Linguistics: ACL 2023</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>Several explanation methods such as Integrated Gradients (IG) can be characterised as path-based methods, as they rely on a straight line between the data and an uninformative baseline. However, when applied to language models, these methods produce a path for each word of a sentence simultaneously, which could lead to creating sentences from interpolated words either having no clear meaning, or having a significantly different meaning compared to the original sentence. In order to keep the meaning of these sentences as close as possible to the original one, we propose Sequential Integrated Gradients (SIG), which computes the importance of each word in a sentence by keeping fixed every other words, only creating interpolations between the baseline and the word of interest. Moreover, inspired by the training procedure of language models, we also propose to replace the baseline token “pad” with the trained token “mask”. While being a simple improvement over the original IG method, we show on various models and datasets that SIG proves to be a very effective method for explaining language models.</abstract>
    <identifier type="citekey">enguehard-2023-sequential</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.477</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.477</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>7555</start>
            <end>7565</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Sequential Integrated Gradients: a simple but effective method for explaining language models
%A Enguehard, Joseph
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F enguehard-2023-sequential
%X Several explanation methods such as Integrated Gradients (IG) can be characterised as path-based methods, as they rely on a straight line between the data and an uninformative baseline. However, when applied to language models, these methods produce a path for each word of a sentence simultaneously, which could lead to creating sentences from interpolated words either having no clear meaning, or having a significantly different meaning compared to the original sentence. In order to keep the meaning of these sentences as close as possible to the original one, we propose Sequential Integrated Gradients (SIG), which computes the importance of each word in a sentence by keeping fixed every other words, only creating interpolations between the baseline and the word of interest. Moreover, inspired by the training procedure of language models, we also propose to replace the baseline token “pad” with the trained token “mask”. While being a simple improvement over the original IG method, we show on various models and datasets that SIG proves to be a very effective method for explaining language models.
%R 10.18653/v1/2023.findings-acl.477
%U https://aclanthology.org/2023.findings-acl.477
%U https://doi.org/10.18653/v1/2023.findings-acl.477
%P 7555-7565

Markdown (Informal)

[Sequential Integrated Gradients: a simple but effective method for explaining language models](https://aclanthology.org/2023.findings-acl.477) (Enguehard, Findings 2023)

• Sequential Integrated Gradients: a simple but effective method for explaining language models (Enguehard, Findings 2023)

ACL

• Joseph Enguehard. 2023. Sequential Integrated Gradients: a simple but effective method for explaining language models. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7555–7565, Toronto, Canada. Association for Computational Linguistics.