RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training

Jaehyung Kim, Yuning Mao, Rui Hou, Hanchao Yu, Davis Liang, Pascale Fung, Qifan Wang, Fuli Feng, Lifu Huang, Madian Khabsa

Findings: Machine Learning for NLP Findings Paper