thu-coai/Safety-Prompts

• highreadme#1

  Clarify the primary purpose of this repository in the README's opening

  Why:

  CURRENT

  Chinese safety prompts for evaluating and improving the safety of LLMs.
  
  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。

  COPY-PASTE FIX

  Copy

  This repository provides a comprehensive dataset of Chinese safety prompts and LLM responses, primarily designed for training and fine-tuning safer large language models. 中文安全prompts数据集，主要用于训练和微调更安全的LLM。While originating from our safety evaluation research, for current model evaluation, please refer to our dedicated platforms like SafetyBench.

  OpenDoneDismiss
• mediumtopics#2

  Add more specific topics related to datasets, benchmarks, and adversarial prompts

  Why:

  CURRENT

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

  COPY-PASTE FIX

  Copy

  attack-defense, adversarial-prompts, llm-safety-dataset, llm-benchmark, red-teaming, chatgpt, chinese-language, instruction, llm, prompt, prompt-engineering, safety

  OpenDoneDismiss
• lowabout#3

  Update the repository description to reflect its primary use for training and fine-tuning

  Why:

  CURRENT

  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。

  COPY-PASTE FIX

  Copy

  A comprehensive dataset of Chinese safety prompts and LLM responses, primarily for training and fine-tuning safer large language models. 中文安全prompts数据集，主要用于训练和微调更安全的LLM。

  OpenDoneDismiss

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• CATEGORY QUERY

  How to evaluate and improve the safety of large language models for Chinese language applications?

  you: not recommended
  AI recommended (in order):

  1. Hugging Face Transformers Library
  2. BERT-base-chinese
  3. RoBERTa-large-chinese
  4. Baichuan2-7B-Chat
  5. Qwen-7B-Chat
  6. RealToxicityPrompts
  7. BOLD
  8. TruthfulQA
  9. LM-Harness (EleutherAI/lm-evaluation-harness)
  10. trl library
  11. OpenAI API
  12. GPT-4
  13. GPT-3.5 Turbo
  14. Content Moderation API
  15. Baidu ERNIE Bot API
  16. Alibaba Tongyi Qianwen API
  17. ERNIE Bot
  18. Tongyi Qianwen
  19. Label Studio
  20. Prodigy
  21. Microsoft's Guidance

  AI recommended 21 alternatives but never named thu-coai/Safety-Prompts. This is the gap to close.

  Show full AI answer
• CATEGORY QUERY

  Seeking a dataset of adversarial prompts to test and fine-tune LLM safety.

  you: not recommended
  AI recommended (in order):

  1. AdvBench
  2. HarmBench
  3. Anthropic's Red Teaming Dataset
  4. RealToxicityPrompts
  5. Jailbreak Chat
  6. AdvGLUE

  AI recommended 6 alternatives but never named thu-coai/Safety-Prompts. This is the gap to close.

  Show full AI answer

• Metadata completeness

  pass

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of thu-coai/Safety-Prompts?

  pass
  ✓AI named thu-coai/Safety-Prompts explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• If a team adopts thu-coai/Safety-Prompts in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI named thu-coai/Safety-Prompts explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• In one sentence, what problem does the repo thu-coai/Safety-Prompts solve, and who is the primary audience?

  pass
  ⚠AI did not name thu-coai/Safety-Prompts — likely talking about a different project

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?