182 citations · 356 across the 13 of their papers we have counts for
Showing 2022 · cs.CLShow all
2 papers · 2 filters
cs.CL2022
SemAttack: Natural Textual Attacks via Different Semantic Spaces
Boxin Wang, Chejian Xu, Xiangyu Liu +2
Recent studies show that pre-trained language models (LMs) are vulnerable to textual adversarial attacks. However, existing attack methods either suffer from low attack success rat…
cs.CL2022★ 20 cited
Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models
Boxin Wang, Wei Ping, Chaowei Xiao +6
Pre-trained language models (LMs) are shown to easily generate toxic language. In this work, we systematically explore domain-adaptive training to reduce the toxicity of language m…