<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cifka-liutkus-2023-black">
    <titleInfo>
        <title>Black-box language model explanation by context length probing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ondřej</namePart>
        <namePart type="family">Cífka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Antoine</namePart>
        <namePart type="family">Liutkus</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>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</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>The increasingly widespread adoption of large language models has highlighted the need for improving their explainability. We present *context length probing*, a novel explanation technique for causal language models, based on tracking the predictions of a model as a function of the length of available context, and allowing to assign *differential importance scores* to different contexts. The technique is model-agnostic and does not rely on access to model internals beyond computing token-level probabilities. We apply context length probing to large pre-trained language models and offer some initial analyses and insights, including the potential for studying long-range dependencies. The [source code](https://github.com/cifkao/context-probing/) and an [interactive demo](https://cifkao.github.io/context-probing/) of the method are available.</abstract>
    <identifier type="citekey">cifka-liutkus-2023-black</identifier>
    <identifier type="doi">10.18653/v1/2023.acl-short.92</identifier>
    <location>
        <url>https://aclanthology.org/2023.acl-short.92</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>1067</start>
            <end>1079</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Black-box language model explanation by context length probing
%A Cífka, Ondřej
%A Liutkus, Antoine
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F cifka-liutkus-2023-black
%X The increasingly widespread adoption of large language models has highlighted the need for improving their explainability. We present *context length probing*, a novel explanation technique for causal language models, based on tracking the predictions of a model as a function of the length of available context, and allowing to assign *differential importance scores* to different contexts. The technique is model-agnostic and does not rely on access to model internals beyond computing token-level probabilities. We apply context length probing to large pre-trained language models and offer some initial analyses and insights, including the potential for studying long-range dependencies. The [source code](https://github.com/cifkao/context-probing/) and an [interactive demo](https://cifkao.github.io/context-probing/) of the method are available.
%R 10.18653/v1/2023.acl-short.92
%U https://aclanthology.org/2023.acl-short.92
%U https://doi.org/10.18653/v1/2023.acl-short.92
%P 1067-1079

Markdown (Informal)

[Black-box language model explanation by context length probing](https://aclanthology.org/2023.acl-short.92) (Cífka & Liutkus, ACL 2023)

• Black-box language model explanation by context length probing (Cífka & Liutkus, ACL 2023)

ACL

• Ondřej Cífka and Antoine Liutkus. 2023. Black-box language model explanation by context length probing. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1067–1079, Toronto, Canada. Association for Computational Linguistics.