<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uppaal-etal-2023-fine">
    <titleInfo>
        <title>Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rheeya</namePart>
        <namePart type="family">Uppaal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junjie</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yixuan</namePart>
        <namePart type="family">Li</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 1: Long 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>Out-of-distribution (OOD) detection is a critical task for reliable predictions over text. Fine-tuning with pre-trained language models has been a de facto procedure to derive OOD detectors with respect to in-distribution (ID) data. Despite its common use, the understanding of the role of fine-tuning and its necessity for OOD detection is largely unexplored. In this paper, we raise the question: is fine-tuning necessary for OOD detection? We present a study investigating the efficacy of directly leveraging pre-trained language models for OOD detection, without any model fine-tuning on the ID data. We compare the approach with several competitive fine-tuning objectives, and offer new insights under various types of distributional shifts. Extensive experiments demonstrate near-perfect OOD detection performance (with 0% FPR95 in many cases), strongly outperforming the fine-tuned counterpart.</abstract>
    <identifier type="citekey">uppaal-etal-2023-fine</identifier>
    <identifier type="doi">10.18653/v1/2023.acl-long.717</identifier>
    <location>
        <url>https://aclanthology.org/2023.acl-long.717</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>12813</start>
            <end>12832</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection
%A Uppaal, Rheeya
%A Hu, Junjie
%A Li, Yixuan
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F uppaal-etal-2023-fine
%X Out-of-distribution (OOD) detection is a critical task for reliable predictions over text. Fine-tuning with pre-trained language models has been a de facto procedure to derive OOD detectors with respect to in-distribution (ID) data. Despite its common use, the understanding of the role of fine-tuning and its necessity for OOD detection is largely unexplored. In this paper, we raise the question: is fine-tuning necessary for OOD detection? We present a study investigating the efficacy of directly leveraging pre-trained language models for OOD detection, without any model fine-tuning on the ID data. We compare the approach with several competitive fine-tuning objectives, and offer new insights under various types of distributional shifts. Extensive experiments demonstrate near-perfect OOD detection performance (with 0% FPR95 in many cases), strongly outperforming the fine-tuned counterpart.
%R 10.18653/v1/2023.acl-long.717
%U https://aclanthology.org/2023.acl-long.717
%U https://doi.org/10.18653/v1/2023.acl-long.717
%P 12813-12832

Markdown (Informal)

[Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection](https://aclanthology.org/2023.acl-long.717) (Uppaal et al., ACL 2023)

• Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection (Uppaal et al., ACL 2023)

ACL

• Rheeya Uppaal, Junjie Hu, and Yixuan Li. 2023. Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12813–12832, Toronto, Canada. Association for Computational Linguistics.