all InfoSec news
Understanding Multi-Turn Toxic Behaviors in Open-Domain Chatbots. (arXiv:2307.09579v1 [cs.CR])
cs.CR updates on arXiv.org arxiv.org
Recent advances in natural language processing and machine learning have led
to the development of chatbot models, such as ChatGPT, that can engage in
conversational dialogue with human users. However, the ability of these models
to generate toxic or harmful responses during a non-toxic multi-turn
conversation remains an open research question. Existing research focuses on
single-turn sentence testing, while we find that 82\% of the individual
non-toxic sentences that elicit toxic behaviors in a conversation are
considered safe by existing …
chatbot chatbots chatgpt conversation development domain human language led machine machine learning natural language natural language processing non question research toxic turn understanding