Debiasing Stance Detection Models with Counterfactual Reasoning and Adversarial Bias Learning
This work addresses bias in stance detection for NLP applications, offering an incremental improvement by better disentangling bias from stance features.
The paper tackles the problem of dataset bias in stance detection models, where models rely on spurious correlations in text rather than learning target-text interactions, and proposes a counterfactual reasoning framework with adversarial bias learning to mitigate this bias, achieving improved performance over existing debiasing baselines on original and new test sets.
Stance detection models may tend to rely on dataset bias in the text part as a shortcut and thus fail to sufficiently learn the interaction between the targets and texts. Recent debiasing methods usually treated features learned by small models or big models at earlier steps as bias features and proposed to exclude the branch learning those bias features during inference. However, most of these methods fail to disentangle the ``good'' stance features and ``bad'' bias features in the text part. In this paper, we investigate how to mitigate dataset bias in stance detection. Motivated by causal effects, we leverage a novel counterfactual inference framework, which enables us to capture the dataset bias in the text part as the direct causal effect of the text on stances and reduce the dataset bias in the text part by subtracting the direct text effect from the total causal effect. We novelly model bias features as features that correlate with the stance labels but fail on intermediate stance reasoning subtasks and propose an adversarial bias learning module to model the bias more accurately. To verify whether our model could better model the interaction between texts and targets, we test our model on recently proposed test sets to evaluate the understanding of the task from various aspects. Experiments demonstrate that our proposed method (1) could better model the bias features, and (2) outperforms existing debiasing baselines on both the original dataset and most of the newly constructed test sets.