@inproceedings{kim-etal-2023-roast,
title = "{R}o{AST}: Robustifying Language Models via Adversarial Perturbation with Selective Training",
author = "Kim, Jaehyung and
Mao, Yuning and
Hou, Rui and
Yu, Hanchao and
Liang, Davis and
Fung, Pascale and
Wang, Qifan and
Feng, Fuli and
Huang, Lifu and
Khabsa, Madian",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.223",
doi = "10.18653/v1/2023.findings-emnlp.223",
pages = "3412--3444",
abstract = "Fine-tuning pre-trained language models (LMs) has become the de facto standard in many NLP tasks. Nevertheless, fine-tuned LMs are still prone to robustness issues, such as adversarial robustness and model calibration. Several perspectives of robustness for LMs have been studied independently, but lacking a unified consideration in multiple perspectives. In this paper, we propose Robustifying LMs via Adversarial perturbation with Selective Training (RoAST), a simple yet effective fine-tuning technique to enhance the multi-perspective robustness of LMs in a unified way. RoAST effectively incorporates two important sources for the model robustness, robustness on the perturbed inputs and generalizable knowledge in pre-trained LMs. To be specific, RoAST introduces adversarial perturbation during fine-tuning while the model parameters are selectively updated upon their relative importance to minimize unnecessary deviation. Under a unified evaluation of fine-tuned LMs by incorporating four representative perspectives of model robustness, we demonstrate the effectiveness of RoAST compared to state-of-the-art fine-tuning methods on six different types of LMs, which indicates its usefulness in practice.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2023-roast">
<titleInfo>
<title>RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jaehyung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuning</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanchao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davis</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qifan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuli</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifu</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madian</namePart>
<namePart type="family">Khabsa</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>Fine-tuning pre-trained language models (LMs) has become the de facto standard in many NLP tasks. Nevertheless, fine-tuned LMs are still prone to robustness issues, such as adversarial robustness and model calibration. Several perspectives of robustness for LMs have been studied independently, but lacking a unified consideration in multiple perspectives. In this paper, we propose Robustifying LMs via Adversarial perturbation with Selective Training (RoAST), a simple yet effective fine-tuning technique to enhance the multi-perspective robustness of LMs in a unified way. RoAST effectively incorporates two important sources for the model robustness, robustness on the perturbed inputs and generalizable knowledge in pre-trained LMs. To be specific, RoAST introduces adversarial perturbation during fine-tuning while the model parameters are selectively updated upon their relative importance to minimize unnecessary deviation. Under a unified evaluation of fine-tuned LMs by incorporating four representative perspectives of model robustness, we demonstrate the effectiveness of RoAST compared to state-of-the-art fine-tuning methods on six different types of LMs, which indicates its usefulness in practice.</abstract>
<identifier type="citekey">kim-etal-2023-roast</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.223</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.223</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>3412</start>
<end>3444</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training
%A Kim, Jaehyung
%A Mao, Yuning
%A Hou, Rui
%A Yu, Hanchao
%A Liang, Davis
%A Fung, Pascale
%A Wang, Qifan
%A Feng, Fuli
%A Huang, Lifu
%A Khabsa, Madian
%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 kim-etal-2023-roast
%X Fine-tuning pre-trained language models (LMs) has become the de facto standard in many NLP tasks. Nevertheless, fine-tuned LMs are still prone to robustness issues, such as adversarial robustness and model calibration. Several perspectives of robustness for LMs have been studied independently, but lacking a unified consideration in multiple perspectives. In this paper, we propose Robustifying LMs via Adversarial perturbation with Selective Training (RoAST), a simple yet effective fine-tuning technique to enhance the multi-perspective robustness of LMs in a unified way. RoAST effectively incorporates two important sources for the model robustness, robustness on the perturbed inputs and generalizable knowledge in pre-trained LMs. To be specific, RoAST introduces adversarial perturbation during fine-tuning while the model parameters are selectively updated upon their relative importance to minimize unnecessary deviation. Under a unified evaluation of fine-tuned LMs by incorporating four representative perspectives of model robustness, we demonstrate the effectiveness of RoAST compared to state-of-the-art fine-tuning methods on six different types of LMs, which indicates its usefulness in practice.
%R 10.18653/v1/2023.findings-emnlp.223
%U https://aclanthology.org/2023.findings-emnlp.223
%U https://doi.org/10.18653/v1/2023.findings-emnlp.223
%P 3412-3444
Markdown (Informal)
[RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training](https://aclanthology.org/2023.findings-emnlp.223) (Kim et al., Findings 2023)
ACL
- Jaehyung Kim, Yuning Mao, Rui Hou, Hanchao Yu, Davis Liang, Pascale Fung, Qifan Wang, Fuli Feng, Lifu Huang, and Madian Khabsa. 2023. RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3412–3444, Singapore. Association for Computational Linguistics.