<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miglani-etal-2023-using">
    <titleInfo>
        <title>Using Captum to Explain Generative Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vivek</namePart>
        <namePart type="family">Miglani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aobo</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aram</namePart>
        <namePart type="family">Markosyan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Diego</namePart>
        <namePart type="family">Garcia-Olano</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Narine</namePart>
        <namePart type="family">Kokhlikyan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Liling</namePart>
            <namePart type="family">Tan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Dmitrijs</namePart>
            <namePart type="family">Milajevs</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Geeticka</namePart>
            <namePart type="family">Chauhan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jeremy</namePart>
            <namePart type="family">Gwinnup</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Elijah</namePart>
            <namePart type="family">Rippeth</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Captum is a comprehensive library for model explainability in PyTorch, offering a range of methods from the interpretability literature to enhance users’ understanding of PyTorch models. In this paper, we introduce new features in Captum that are specifically designed to analyze the behavior of generative language models. We provide an overview of the available functionalities and example applications of their potential for understanding learned associations within generative language models.</abstract>
    <identifier type="citekey">miglani-etal-2023-using</identifier>
    <identifier type="doi">10.18653/v1/2023.nlposs-1.19</identifier>
    <location>
        <url>https://aclanthology.org/2023.nlposs-1.19</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>165</start>
            <end>173</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Using Captum to Explain Generative Language Models
%A Miglani, Vivek
%A Yang, Aobo
%A Markosyan, Aram
%A Garcia-Olano, Diego
%A Kokhlikyan, Narine
%Y Tan, Liling
%Y Milajevs, Dmitrijs
%Y Chauhan, Geeticka
%Y Gwinnup, Jeremy
%Y Rippeth, Elijah
%S Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F miglani-etal-2023-using
%X Captum is a comprehensive library for model explainability in PyTorch, offering a range of methods from the interpretability literature to enhance users’ understanding of PyTorch models. In this paper, we introduce new features in Captum that are specifically designed to analyze the behavior of generative language models. We provide an overview of the available functionalities and example applications of their potential for understanding learned associations within generative language models.
%R 10.18653/v1/2023.nlposs-1.19
%U https://aclanthology.org/2023.nlposs-1.19
%U https://doi.org/10.18653/v1/2023.nlposs-1.19
%P 165-173

Markdown (Informal)

[Using Captum to Explain Generative Language Models](https://aclanthology.org/2023.nlposs-1.19) (Miglani et al., NLPOSS-WS 2023)

• Using Captum to Explain Generative Language Models (Miglani et al., NLPOSS-WS 2023)

ACL

• Vivek Miglani, Aobo Yang, Aram Markosyan, Diego Garcia-Olano, and Narine Kokhlikyan. 2023. Using Captum to Explain Generative Language Models. In Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023), pages 165–173, Singapore. Association for Computational Linguistics.