S
Safety-Prompts
thu-coai/Safety-Prompts
Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。
★1.2kstars
Apache-2.0
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?Security & Governance project leveraging attack-defense and chatgpt, open-source
Who made it?Maintained by thu-coai team, 1.2K⭐ on GitHub, #108 out of 413 in Security & Governance
Why does it exist?As the Security & Governance landscape evolved, the thu-coai team identified the need for better attack-defense solutions. Safety-Prompts was created to simplify chatgpt workflows.
What can it do?Key use cases: chinese-language, instruction, llm
How to install with AI?Use an AI coding assistant to follow the README and automatically handle the install and environment setup.
🔗 github.com/thu-coai/Safety-Prompts | 官网 http://coai.cs.tsinghua.edu.cn/leaderboard/
🔗 github.com/thu-coai/Safety-Prompts | 官网 http://coai.cs.tsinghua.edu.cn/leaderboard/
Topics
attack-defensechatgptchinese-languageinstructionllmpromptprompt-engineeringsafety