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。
Apache-2.0
Issues
- 1
instruction_attack_scenarios.json里包含关于**的不当数据
#22 opened by wusi1590 - 2
自动化评估方法有哪些?
#9 opened by potong - 1
数据集的回复部分有用专门的安全相关prompt吗?
#21 opened by IcyFeather233 - 1
What model is the LLM used in Figure 3?
#20 opened by XiaoluJiayou - 3
Why the sensitive topics are missing?
#17 opened by HuangHaoyu1997 - 3
- 3
请问访问评测平台一定要清华内网吗?
#18 opened by Ligandlly - 1
Missing models?
#16 opened by zhimin-z - 2
- 1
请问这里提供的数据和safetyBench中用于测试的数据是同一份吗?
#14 opened by WinncyNing - 1
多项选择题的安全评测数据集哪里可以下载?
#13 opened by gongjunjin - 0
多项选择题的安全评测数据集哪里可以下载?
#12 opened by gongjunjin - 1
数据集包含标准答案吗
#11 opened by demi543 - 1
在平台上提交了公开数据集的评测结果,但是一直没出结果。
#8 opened by fengyh3 - 1
- 1
这些数据是正确的吗?
#5 opened by guozhiyao - 1
无法进入安全评测平台
#6 opened by WenjingBao - 1
请问不同场景下评测时使用的prompt后续会开源吗
#4 opened by lierer007 - 5
- 3
模型增广方法是否会开源
#1 opened by hutbery - 2
手工标注的prompt
#3 opened by zhuang-li