Mitigating the Inconsistency Between Word Saliency and Model Confidence with Pathological Contrastive Training Pengwei Zhan author Yang Wu author Shaolei Zhou author Yunjian Zhang author Liming Wang 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 zhan-etal-2022-mitigating 10.18653/v1/2022.findings-acl.175 https://aclanthology.org/2022.findings-acl.175/ 2022-05 2226 2244