@inproceedings{ouyang-etal-2023-prefix,
title = "On Prefix-tuning for Lightweight Out-of-distribution Detection",
author = "Ouyang, Yawen and
Cao, Yongchang and
Gao, Yuan and
Wu, Zhen and
Zhang, Jianbing and
Dai, Xinyu",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.85",
doi = "10.18653/v1/2023.acl-long.85",
pages = "1533--1545",
abstract = "Out-of-distribution (OOD) detection, a fundamental task vexing real-world applications, has attracted growing attention in the NLP community. Recently fine-tuning based methods have made promising progress. However, it could be costly to store fine-tuned models for each scenario. In this paper, we depart from the classic fine-tuning based OOD detection toward a parameter-efficient alternative, and propose an unsupervised prefix-tuning based OOD detection framework termed PTO. Additionally, to take advantage of optional training data labels and targeted OOD data, two practical extensions of PTO are further proposed. Overall, PTO and its extensions offer several key advantages of being lightweight, easy-to-reproduce, and theoretically justified. Experimental results show that our methods perform comparably to, even better than, existing fine-tuning based OOD detection approaches under a wide range of metrics, detection settings, and OOD types.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ouyang-etal-2023-prefix">
<titleInfo>
<title>On Prefix-tuning for Lightweight Out-of-distribution Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yawen</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongchang</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianbing</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="family">Dai</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, a fundamental task vexing real-world applications, has attracted growing attention in the NLP community. Recently fine-tuning based methods have made promising progress. However, it could be costly to store fine-tuned models for each scenario. In this paper, we depart from the classic fine-tuning based OOD detection toward a parameter-efficient alternative, and propose an unsupervised prefix-tuning based OOD detection framework termed PTO. Additionally, to take advantage of optional training data labels and targeted OOD data, two practical extensions of PTO are further proposed. Overall, PTO and its extensions offer several key advantages of being lightweight, easy-to-reproduce, and theoretically justified. Experimental results show that our methods perform comparably to, even better than, existing fine-tuning based OOD detection approaches under a wide range of metrics, detection settings, and OOD types.</abstract>
<identifier type="citekey">ouyang-etal-2023-prefix</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.85</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.85</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1533</start>
<end>1545</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Prefix-tuning for Lightweight Out-of-distribution Detection
%A Ouyang, Yawen
%A Cao, Yongchang
%A Gao, Yuan
%A Wu, Zhen
%A Zhang, Jianbing
%A Dai, Xinyu
%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 ouyang-etal-2023-prefix
%X Out-of-distribution (OOD) detection, a fundamental task vexing real-world applications, has attracted growing attention in the NLP community. Recently fine-tuning based methods have made promising progress. However, it could be costly to store fine-tuned models for each scenario. In this paper, we depart from the classic fine-tuning based OOD detection toward a parameter-efficient alternative, and propose an unsupervised prefix-tuning based OOD detection framework termed PTO. Additionally, to take advantage of optional training data labels and targeted OOD data, two practical extensions of PTO are further proposed. Overall, PTO and its extensions offer several key advantages of being lightweight, easy-to-reproduce, and theoretically justified. Experimental results show that our methods perform comparably to, even better than, existing fine-tuning based OOD detection approaches under a wide range of metrics, detection settings, and OOD types.
%R 10.18653/v1/2023.acl-long.85
%U https://aclanthology.org/2023.acl-long.85
%U https://doi.org/10.18653/v1/2023.acl-long.85
%P 1533-1545
Markdown (Informal)
[On Prefix-tuning for Lightweight Out-of-distribution Detection](https://aclanthology.org/2023.acl-long.85) (Ouyang et al., ACL 2023)
ACL
- Yawen Ouyang, Yongchang Cao, Yuan Gao, Zhen Wu, Jianbing Zhang, and Xinyu Dai. 2023. On Prefix-tuning for Lightweight Out-of-distribution Detection. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1533–1545, Toronto, Canada. Association for Computational Linguistics.