Large language models (LLMs) are increasingly used in business dialogue systems but they pose security and ethical risks. Multi-turn conversations, where context influences the model's behavior, can be exploited to produce undesired responses. In this paper, we examine the effectiveness of utilizing off-the-shelf LLMs in straightforward red-teaming approaches, where an attacker LLM aims to elicit undesired output from a target LLM, comparing both single-turn and conversational red-teaming tactics. Our experiments offer insights into various usage strategies that significantly affect their performance as red teamers. They suggest that off-the-shelf models can act as effective red teamers and even adjust their attack strategy based on past attempts, although their effectiveness decreases with greater alignment.
Conversational Complexity for Assessing Risk in Large Language Models
University of Cambridge（剑桥大学）；Spanish National Research Council（西班牙国家研究委员会）；Universitat Politècnica de València（瓦伦西亚理工大学）；Leverhulme Centre for the Future of Intelligence（勒沃休姆未来智能中心）；Center for Automation and Robotics（自动化与机器人中心）；Valencian Research Institute for Artificial Intelligence（瓦伦西亚人工智能研究所）
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
University of California, Los Angeles（加州大学洛杉矶分校）；University of Washington（华盛顿大学）；Qatar Computing Research Institute（卡塔尔计算研究所）；Google（谷歌）；Stanford University（斯坦福大学）
Unleashing Large Language Models' Proficiency in Zero-shot Essay Scoring
National Key Laboratory for Multimedia Information Processing, Peking University（北京大学多媒体信息处理国家重点实验室）；School of Computer Science, Peking University（北京大学计算机学院）；School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）
