The paper studies a newly proposed data augmentation method Mixup from a calibration perspective. The authors empirically show that models trained with Mixup are significantly better calibrated, in terms of the correlation between the predicted softmax score and the actual likelihood of a correct prediction, when compared to models trained without Mixup. The empirical studies of the paper also show that mixup-trained models are less prone to over-confident prediction on out-of-distribution data, and the label smoothing in Mixup is critical for achieving the desirable calibration outcomes. The paper is well written and easy to follow. The new view of looking into the newly proposed data augmentation method Mixup is interesting and could be practically useful for application where uncertainty is a significant concern.

Recent language models have shown remarkable performance on natural language understanding (NLU) tasks. However, they are often sub-optimal when faced with ambiguous samples that can be interpreted in multiple ways, over-confidently predicting a single label without consideration for its correctness. To address this issue, we propose a novel self-knowledge distillation method that enables models to learn label distributions more accurately by leveraging knowledge distilled from their lower layers. This approach also includes a learning phase that re-calibrates the unnecessarily strengthened confidence for training samples judged as extremely ambiguous based on the distilled distribution knowledge. We validate our method on diverse NLU benchmark datasets and the experimental results demonstrate its effectiveness in producing better label distributions. Particularly, through the process of re-calibrating the confidence for highly ambiguous samples, the issue of over-confidence when predictions for unseen samples do not match with their ground-truth labels has been significantly alleviated. This has been shown to contribute to generating better distributions than the existing state-of-the-art method. Moreover, our method is more efficient in training the models compared to the existing method, as it does not involve additional training processes to refine label distributions.

Research interests in the robustness of deep neural networks against domain shifts have been rapidly increasing in recent years. Most existing works, however, focus on improving the accuracy of the model, not the calibration performance which is another important requirement for trustworthy AI systems. Temperature scaling (TS), an accuracy-preserving post-hoc calibration method, has been proven to be effective in in-domain settings, but not in out-of-domain (OOD) due to the difficulty in obtaining a validation set for the unseen domain beforehand. In this paper, we propose consistency-guided temperature scaling (CTS), a new temperature scaling strategy that can significantly enhance the OOD calibration performance by providing mutual supervision among data samples in the source domains. Motivated by our observation that over-confidence stemming from inconsistent sample predictions is the main obstacle to OOD calibration, we propose to guide the scaling process by taking consistencies into account in terms of two different aspects -- style and content -- which are the key components that can well-represent data samples in multi-domain settings. Experimental results demonstrate that our proposed strategy outperforms existing works, achieving superior OOD calibration performance on various datasets. This can be accomplished by employing only the source domains without compromising accuracy, making our scheme directly applicable to various trustworthy AI systems.