<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xie-etal-2023-proto">
    <titleInfo>
        <title>Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sean</namePart>
        <namePart type="family">Xie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Soroush</namePart>
        <namePart type="family">Vosoughi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Saeed</namePart>
        <namePart type="family">Hassanpour</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>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</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>Large Language Models (LLMs) have significantly advanced the field of Natural Language Processing (NLP), but their lack of interpretability has been a major concern. Current methods for interpreting LLMs are post hoc, applied after inference time, and have limitations such as their focus on low-level features and lack of explainability at higher-level text units. In this work, we introduce proto-lm, a prototypical network-based white-box framework that allows LLMs to learn immediately interpretable embeddings during the fine-tuning stage while maintaining competitive performance. Our method‘s applicability and interpretability are demonstrated through experiments on a wide range of NLP tasks, and our results indicate a new possibility of creating interpretable models without sacrificing performance. This novel approach to interpretability in LLMs can pave the way for more interpretable models without the need to sacrifice performance. We release our code at https://github.com/yx131/proto-lm.</abstract>
    <identifier type="citekey">xie-etal-2023-proto</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.261</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.261/</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>3964</start>
            <end>3979</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models
%A Xie, Sean
%A Vosoughi, Soroush
%A Hassanpour, Saeed
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F xie-etal-2023-proto
%X Large Language Models (LLMs) have significantly advanced the field of Natural Language Processing (NLP), but their lack of interpretability has been a major concern. Current methods for interpreting LLMs are post hoc, applied after inference time, and have limitations such as their focus on low-level features and lack of explainability at higher-level text units. In this work, we introduce proto-lm, a prototypical network-based white-box framework that allows LLMs to learn immediately interpretable embeddings during the fine-tuning stage while maintaining competitive performance. Our method‘s applicability and interpretability are demonstrated through experiments on a wide range of NLP tasks, and our results indicate a new possibility of creating interpretable models without sacrificing performance. This novel approach to interpretability in LLMs can pave the way for more interpretable models without the need to sacrifice performance. We release our code at https://github.com/yx131/proto-lm.
%R 10.18653/v1/2023.findings-emnlp.261
%U https://aclanthology.org/2023.findings-emnlp.261/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.261
%P 3964-3979

Markdown (Informal)

[Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models](https://aclanthology.org/2023.findings-emnlp.261/) (Xie et al., Findings 2023)

• Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models (Xie et al., Findings 2023)

ACL

• Sean Xie, Soroush Vosoughi, and Saeed Hassanpour. 2023. Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3964–3979, Singapore. Association for Computational Linguistics.