Self-Guard: Empower the LLM to Safeguard Itself

arXiv:2310.15851v2 Announce Type: replace
Abstract: The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Currently, there are two main approaches to address jailbreak attacks: safety training and safeguards. Safety training focuses on further training LLM to enhance its safety. On the other hand, safeguards involve implementing external models or filters to prevent harmful outputs. However, safety training has constraints in its ability …

abstract arxiv attacks consequences cs.cl jailbreak language language model large language large language model llm misuse negative safeguards safety safety measures training type