https://github.com/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。
https://github.com/thu-coai/Safety-Prompts

attack-defense chatgpt chinese-language instruction llm prompt prompt-engineering safety

Last synced: about 2 months ago
JSON representation

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。

• Host: GitHub
• URL: https://github.com/thu-coai/Safety-Prompts
• Owner: thu-coai
• License: apache-2.0
• Created: 2023-04-18T14:10:26.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-02-27T08:42:12.000Z (10 months ago)
• Last Synced: 2024-10-18T21:59:40.555Z (about 2 months ago)
• Topics: attack-defense, chatgpt, chinese-language, instruction, llm, prompt, prompt-engineering, safety
• Homepage: http://coai.cs.tsinghua.edu.cn/leaderboard/
• Size: 19.7 MB
• Stars: 858
• Watchers: 7
• Forks: 81
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-instruction-dataset - (thu-coai/Safety-Prompts)|100k|CN|MT|MIX
• awesome-instruction-datasets - thu-coai/Safety-Prompts - coai/Safety-Prompts](https://huggingface.co/datasets/thu-coai/Safety-Prompts) | thu-coai | 100k | Chinese | 中文安全prompts，用于评测和提升大模型的安全性，将模型的输出与人类的价值观对齐。 | (Statistics)
• StarryDivineSky - thu-coai/Safety-Prompts
• awesome-pretrained-chinese-nlp-models - dataset - Prompts](https://github.com/thu-coai/Safety-Prompts) | [清华大学](https://github.com/thu-coai) | [评测平台](http://115.182.62.166:18000/) | (中文指令数据集)
• awesome-llm-prompt-libraries - Safety Prompts