4 accepted papers
Self-interpretable models are increasingly valued for their inherent explainability. Among them, part-prototype networks stand out by mimicking human reasoning through the use of learned prototypes. However, their explanations often lack stability, becoming sensitive to subtle input perturbations. I
Pre-trained language models (PLMs) learn gender bias from imbalances in human-written corpora. This bias leads to critical social issues when deploying PLMs in real-world scenarios. However, minimizing bias is limited by the trade-off due to the degradation of language modeling performance. It is pa…
Revealing the transparency of Deep Neural Networks (DNNs) has been widely studied to describe the decision mechanisms of network inner structures. In this paper, we propose a novel post-hoc framework, Unfold and Conquer Attribution Guidance (UCAG), which enhances the explainability of the network de…
The clear transparency of Deep Neural Networks (DNNs) is hampered by complex internal structures and nonlinear transformations along deep hierarchies. In this paper, we propose a new attribution method, Relative Sectional Propagation (RSP), for fully decomposing the output predictions with the chara…