@inproceedings{jiang-2025-learn,
title = "Learn from Failure: Causality-guided Contrastive Learning for Generalizable Implicit Hate Speech Detection",
author = "Jiang, Tianming",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.593/",
pages = "8858--8867",
abstract = "Implicit hate speech presents a significant challenge for automatic detection systems due to its subtlety and ambiguity. Traditional models trained using empirical risk minimization (ERM) often rely on correlations between class labels and spurious attributes, which leads to poor performance on data lacking these correlations. In this paper, we propose a novel approach using causality-guided contrastive learning (CCL) to enhance the generalizability of implicit hate speech detection. Since ERM tends to identify spurious attributes, CCL works by aligning the representations of samples with the same class but opposite spurious attributes, identified through ERM`s inference failure. This method reduces the model`s reliance on spurious correlations, allowing it to learn more robust features and handle diverse, nuanced contexts better. Our extensive experiments on multiple implicit hate speech datasets show that our approach outperforms current state-of-the-art methods in cross-domain generalization."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-2025-learn">
<titleInfo>
<title>Learn from Failure: Causality-guided Contrastive Learning for Generalizable Implicit Hate Speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianming</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Implicit hate speech presents a significant challenge for automatic detection systems due to its subtlety and ambiguity. Traditional models trained using empirical risk minimization (ERM) often rely on correlations between class labels and spurious attributes, which leads to poor performance on data lacking these correlations. In this paper, we propose a novel approach using causality-guided contrastive learning (CCL) to enhance the generalizability of implicit hate speech detection. Since ERM tends to identify spurious attributes, CCL works by aligning the representations of samples with the same class but opposite spurious attributes, identified through ERM‘s inference failure. This method reduces the model‘s reliance on spurious correlations, allowing it to learn more robust features and handle diverse, nuanced contexts better. Our extensive experiments on multiple implicit hate speech datasets show that our approach outperforms current state-of-the-art methods in cross-domain generalization.</abstract>
<identifier type="citekey">jiang-2025-learn</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.593/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>8858</start>
<end>8867</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learn from Failure: Causality-guided Contrastive Learning for Generalizable Implicit Hate Speech Detection
%A Jiang, Tianming
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F jiang-2025-learn
%X Implicit hate speech presents a significant challenge for automatic detection systems due to its subtlety and ambiguity. Traditional models trained using empirical risk minimization (ERM) often rely on correlations between class labels and spurious attributes, which leads to poor performance on data lacking these correlations. In this paper, we propose a novel approach using causality-guided contrastive learning (CCL) to enhance the generalizability of implicit hate speech detection. Since ERM tends to identify spurious attributes, CCL works by aligning the representations of samples with the same class but opposite spurious attributes, identified through ERM‘s inference failure. This method reduces the model‘s reliance on spurious correlations, allowing it to learn more robust features and handle diverse, nuanced contexts better. Our extensive experiments on multiple implicit hate speech datasets show that our approach outperforms current state-of-the-art methods in cross-domain generalization.
%U https://aclanthology.org/2025.coling-main.593/
%P 8858-8867
Markdown (Informal)
[Learn from Failure: Causality-guided Contrastive Learning for Generalizable Implicit Hate Speech Detection](https://aclanthology.org/2025.coling-main.593/) (Jiang, COLING 2025)
ACL