Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue

arXiv:2402.17262v1 Announce Type: new
Abstract: Large Language Models (LLMs) have been demonstrated to generate illegal or unethical responses, particularly when subjected to "jailbreak." Research on jailbreak has highlighted the safety issues of LLMs. However, prior studies have predominantly focused on single-turn dialogue, ignoring the potential complexities and risks presented by multi-turn dialogue, a crucial mode through which humans derive information from LLMs. In this paper, we argue that humans could exploit multi-turn dialogue to induce LLMs into generating harmful information. …

abstract arxiv complexities cs.ai cs.cl dialogue generate jailbreak language language models large language large language models llms prior research responses safety speak studies type vulnerability