@inproceedings{cheng-etal-2025-mitigating,
title = "Mitigating Spurious Correlations via Counterfactual Contrastive Learning",
author = "Cheng, Fengxiang and
Zhou, Chuan and
Li, Xiang and
Leidinger, Alina and
Li, Haoxuan and
Gong, Mingming and
Liu, Fenrong and
Van Rooij, Robert",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.1290/",
pages = "23713--23722",
ISBN = "979-8-89176-335-7",
abstract = "Identifying causal relationships rather than spurious correlations between words and class labels plays a crucial role in building robust text classifiers. Previous studies proposed using causal effects to distinguish words that are causally related to the sentiment, and then building robust text classifiers using words with high causal effects. However, we find that when a sentence has multiple causally related words simultaneously, the magnitude of causal effects will be significantly reduced, which limits the applicability of previous causal effect-based methods in distinguishing causally related words from spuriously correlated ones. To fill this gap, in this paper, we introduce both the probability of necessity (PN) and probability of sufficiency (PS), aiming to answer the counterfactual question that `if a sentence has a certain sentiment in the presence/absence of a word, would the sentiment change in the absence/presence of that word?'. Specifically, we first derive the identifiability of PN and PS under different sentiment monotonicities, and calibrate the estimation of PN and PS via the estimated average treatment effect. Finally, the robust text classifier is built by identifying the words with larger PN and PS as causally related words, and other words as spuriously correlated words, based on a contrastive learning approach name CPNS is proposed to achieve robust sentiment classification. Extensive experiments are conducted on public datasets to validate the effectiveness of our method."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2025-mitigating">
<titleInfo>
<title>Mitigating Spurious Correlations via Counterfactual Contrastive Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fengxiang</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Leidinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoxuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingming</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fenrong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Van Rooij</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Identifying causal relationships rather than spurious correlations between words and class labels plays a crucial role in building robust text classifiers. Previous studies proposed using causal effects to distinguish words that are causally related to the sentiment, and then building robust text classifiers using words with high causal effects. However, we find that when a sentence has multiple causally related words simultaneously, the magnitude of causal effects will be significantly reduced, which limits the applicability of previous causal effect-based methods in distinguishing causally related words from spuriously correlated ones. To fill this gap, in this paper, we introduce both the probability of necessity (PN) and probability of sufficiency (PS), aiming to answer the counterfactual question that ‘if a sentence has a certain sentiment in the presence/absence of a word, would the sentiment change in the absence/presence of that word?’. Specifically, we first derive the identifiability of PN and PS under different sentiment monotonicities, and calibrate the estimation of PN and PS via the estimated average treatment effect. Finally, the robust text classifier is built by identifying the words with larger PN and PS as causally related words, and other words as spuriously correlated words, based on a contrastive learning approach name CPNS is proposed to achieve robust sentiment classification. Extensive experiments are conducted on public datasets to validate the effectiveness of our method.</abstract>
<identifier type="citekey">cheng-etal-2025-mitigating</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.1290/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>23713</start>
<end>23722</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mitigating Spurious Correlations via Counterfactual Contrastive Learning
%A Cheng, Fengxiang
%A Zhou, Chuan
%A Li, Xiang
%A Leidinger, Alina
%A Li, Haoxuan
%A Gong, Mingming
%A Liu, Fenrong
%A Van Rooij, Robert
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F cheng-etal-2025-mitigating
%X Identifying causal relationships rather than spurious correlations between words and class labels plays a crucial role in building robust text classifiers. Previous studies proposed using causal effects to distinguish words that are causally related to the sentiment, and then building robust text classifiers using words with high causal effects. However, we find that when a sentence has multiple causally related words simultaneously, the magnitude of causal effects will be significantly reduced, which limits the applicability of previous causal effect-based methods in distinguishing causally related words from spuriously correlated ones. To fill this gap, in this paper, we introduce both the probability of necessity (PN) and probability of sufficiency (PS), aiming to answer the counterfactual question that ‘if a sentence has a certain sentiment in the presence/absence of a word, would the sentiment change in the absence/presence of that word?’. Specifically, we first derive the identifiability of PN and PS under different sentiment monotonicities, and calibrate the estimation of PN and PS via the estimated average treatment effect. Finally, the robust text classifier is built by identifying the words with larger PN and PS as causally related words, and other words as spuriously correlated words, based on a contrastive learning approach name CPNS is proposed to achieve robust sentiment classification. Extensive experiments are conducted on public datasets to validate the effectiveness of our method.
%U https://aclanthology.org/2025.findings-emnlp.1290/
%P 23713-23722
Markdown (Informal)
[Mitigating Spurious Correlations via Counterfactual Contrastive Learning](https://aclanthology.org/2025.findings-emnlp.1290/) (Cheng et al., Findings 2025)
ACL
- Fengxiang Cheng, Chuan Zhou, Xiang Li, Alina Leidinger, Haoxuan Li, Mingming Gong, Fenrong Liu, and Robert Van Rooij. 2025. Mitigating Spurious Correlations via Counterfactual Contrastive Learning. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 23713–23722, Suzhou, China. Association for Computational Linguistics.