Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Gao, Zuchen"'
As large language models (LLMs) constantly evolve, ensuring their safety remains a critical research problem. Previous red-teaming approaches for LLM safety have primarily focused on single prompt attacks or goal hijacking. To the best of our knowled
Externí odkaz:
http://arxiv.org/abs/2406.17626