<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="manna-sett-2024-faithfulness">
    <titleInfo>
        <title>Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Supriya</namePart>
        <namePart type="family">Manna</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Niladri</namePart>
        <namePart type="family">Sett</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 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yonatan</namePart>
            <namePart type="family">Belinkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Najoung</namePart>
            <namePart type="family">Kim</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jaap</namePart>
            <namePart type="family">Jumelet</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hosein</namePart>
            <namePart type="family">Mohebbi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aaron</namePart>
            <namePart type="family">Mueller</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hanjie</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, US</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Faithfulness is arguably the most critical metric to assess the reliability of explainable AI. In NLP, current methods for faithfulness evaluation are fraught with discrepancies and biases, often failing to capture the true reasoning of models. We introduce Adversarial Sensitivity as a novel approach to faithfulness evaluation, focusing on the explainer’s response when the model is under adversarial attack. Our method accounts for the faithfulness of explainers by capturing sensitivity to adversarial input changes. This work addresses significant limitations in existing evaluation techniques, and furthermore, quantifies faithfulness from a crucial yet underexplored paradigm.</abstract>
    <identifier type="citekey">manna-sett-2024-faithfulness</identifier>
    <location>
        <url>https://aclanthology.org/2024.blackboxnlp-1.12</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>193</start>
            <end>206</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations
%A Manna, Supriya
%A Sett, Niladri
%Y Belinkov, Yonatan
%Y Kim, Najoung
%Y Jumelet, Jaap
%Y Mohebbi, Hosein
%Y Mueller, Aaron
%Y Chen, Hanjie
%S Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, US
%F manna-sett-2024-faithfulness
%X Faithfulness is arguably the most critical metric to assess the reliability of explainable AI. In NLP, current methods for faithfulness evaluation are fraught with discrepancies and biases, often failing to capture the true reasoning of models. We introduce Adversarial Sensitivity as a novel approach to faithfulness evaluation, focusing on the explainer’s response when the model is under adversarial attack. Our method accounts for the faithfulness of explainers by capturing sensitivity to adversarial input changes. This work addresses significant limitations in existing evaluation techniques, and furthermore, quantifies faithfulness from a crucial yet underexplored paradigm.
%U https://aclanthology.org/2024.blackboxnlp-1.12
%P 193-206

Markdown (Informal)

[Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations](https://aclanthology.org/2024.blackboxnlp-1.12) (Manna & Sett, BlackboxNLP 2024)

• Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations (Manna & Sett, BlackboxNLP 2024)

ACL

• Supriya Manna and Niladri Sett. 2024. Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations. In Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 193–206, Miami, Florida, US. Association for Computational Linguistics.