Robust Conversational Agents against Imperceptible Toxicity Triggers. (arXiv:2205.02392v1 [cs.CL])

Warning: this paper contains content that maybe offensive or upsetting.
Recent research in Natural Language Processing (NLP) has advanced the
development of various toxicity detection models with the intention of
identifying and mitigating toxic language from existing systems. Despite the
abundance of research in this area, less attention has been given to
adversarial attacks that force the system to generate toxic language and the
defense against them. Existing work to generate such attacks is either based on
human-generated attacks which …

agents arxiv conversational conversational agents toxicity