arXiv - CSCL: "RoAST: Robustifying Language Models via Adversari…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training. (arXiv:2312.04032v1 [cs.CL])

http://arxiv.org/abs/2312.04032 #arXiv #NLProc

Dec 10, 2023, 03:18 · · arxiv-cscl · · ·

Sign in to participate in the conversation