Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model

Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model Jiayi Wang author Rongzhou Bao author Zhuosheng Zhang author Hai Zhao author 2022-05 text Findings of the Association for Computational Linguistics: ACL 2022 Smaranda Muresan editor Preslav Nakov editor Aline Villavicencio editor Association for Computational Linguistics Dublin, Ireland conference publication wang-etal-2022-distinguishing 10.18653/v1/2022.findings-acl.73 https://aclanthology.org/2022.findings-acl.73/ 2022-05 905 915