2025.emnlp-main.520@ACL

Total: 1

#1 CoBA: Counterbias Text Augmentation for Mitigating Various Spurious Correlations via Semantic Triples [PDF] [Copy] [Kimi] [REL]

Authors: Kyohoon Jin, Juhwan Choi, JungMin Yun, Junho Lee, Soojin Jang, YoungBin Kim

Deep learning models often learn and exploit spurious correlations in training data, using these non-target features to inform their predictions. Such reliance leads to performance degradation and poor generalization on unseen data. To address these limitations, we introduce a more general form of counterfactual data augmentation, termed *counterbias* data augmentation, which simultaneously tackles multiple biases (e.g., gender bias, simplicity bias) and enhances out-of-distribution robustness. We present **CoBA**: **Co**unter**B**ias **A**ugmentation, a unified framework that operates at the semantic triple level: first decomposing text into subject-predicate-object triples, then selectively modifying these triples to disrupt spurious correlations. By reconstructing the text from these adjusted triples, **CoBA** generates *counterbias* data that mitigates spurious patterns. Through extensive experiments, we demonstrate that **CoBA** not only improves downstream task performance, but also effectively reduces biases and strengthens out-of-distribution resilience, offering a versatile and robust solution to the challenges posed by spurious correlations.

Subject: EMNLP.2025 - Main