RobustNLP/CipherChat · AI Repo StatsRORobustNLP/CipherChat
A framework to evaluate the generalization capability of safety alignment for LLMs
LLM & mô hình nền tảngPython MIT 64tạo 2023-08-10 #alignment#chatgpt#gpt-4-0613#jailbreak#large-language-models#llm#security