Prefer a chat interface with context about you and your work?
Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness
Data modification, either via additional training datasets, data augmentation, debiasing, and dataset filtering, has been proposed as an effective solution for generalizing to out-of-domain (OOD) inputs, in both natural language processing and computer vision literature.However, the effect of data modification on adversarial robustness remains unclear.In this work, we conduct a …