no code implementations • 27 Feb 2024 • Zhenhong Zhou, Jiuyang Xiang, Haopeng Chen, Quan Liu, Zherui Li, Sen Su
Large Language Models (LLMs) have been demonstrated to generate illegal or unethical responses, particularly when subjected to "jailbreak."
no code implementations • 30 Aug 2023 • Zhenhong Zhou, Jiuyang Xiang, Chaomeng Chen, Sen Su
Quantifying language model memorization helps evaluate potential privacy risks.