@inproceedings{qiu-etal-2024-paircfr,
title = "{P}air{CFR}: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning",
author = "Qiu, Xiaoqi and
Wang, Yongjie and
Guo, Xu and
Zeng, Zhiwei and
Yue, Yu and
Feng, Yuhong and
Miao, Chunyan",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.646",
pages = "11955--11971",
abstract = "Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robustness against spurious features that happen to correlate with labels by spreading the casual relationships across different classes. Yet, recent research reveals that training with CAD may lead models to overly focus on modified features while ignoring other important contextual information, inadvertently introducing biases that may impair performance on out-of-distribution (OOD) datasets. To mitigate this issue, we employ contrastive learning to promote global feature alignment in addition to learning counterfactual clues. We theoretically prove that contrastive loss can encourage models to leverage a broader range of features beyond those modified ones. Comprehensive experiments on two human-edited CAD datasets demonstrate that our proposed method outperforms the state-of-the-art on OOD datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qiu-etal-2024-paircfr">
<titleInfo>
<title>PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoqi</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiwei</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Yue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunyan</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robustness against spurious features that happen to correlate with labels by spreading the casual relationships across different classes. Yet, recent research reveals that training with CAD may lead models to overly focus on modified features while ignoring other important contextual information, inadvertently introducing biases that may impair performance on out-of-distribution (OOD) datasets. To mitigate this issue, we employ contrastive learning to promote global feature alignment in addition to learning counterfactual clues. We theoretically prove that contrastive loss can encourage models to leverage a broader range of features beyond those modified ones. Comprehensive experiments on two human-edited CAD datasets demonstrate that our proposed method outperforms the state-of-the-art on OOD datasets.</abstract>
<identifier type="citekey">qiu-etal-2024-paircfr</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.646</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>11955</start>
<end>11971</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning
%A Qiu, Xiaoqi
%A Wang, Yongjie
%A Guo, Xu
%A Zeng, Zhiwei
%A Yue, Yu
%A Feng, Yuhong
%A Miao, Chunyan
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F qiu-etal-2024-paircfr
%X Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robustness against spurious features that happen to correlate with labels by spreading the casual relationships across different classes. Yet, recent research reveals that training with CAD may lead models to overly focus on modified features while ignoring other important contextual information, inadvertently introducing biases that may impair performance on out-of-distribution (OOD) datasets. To mitigate this issue, we employ contrastive learning to promote global feature alignment in addition to learning counterfactual clues. We theoretically prove that contrastive loss can encourage models to leverage a broader range of features beyond those modified ones. Comprehensive experiments on two human-edited CAD datasets demonstrate that our proposed method outperforms the state-of-the-art on OOD datasets.
%U https://aclanthology.org/2024.acl-long.646
%P 11955-11971
Markdown (Informal)
[PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning](https://aclanthology.org/2024.acl-long.646) (Qiu et al., ACL 2024)
ACL