Hugging Face's logo

Spaces:
IS2Lab
/
S-Eval_v0.1.1
Building

App Files Community
2
Yuanxh commited on
Commit
8fc3e0f
·
1 Parent(s): 0263348

release v0.1.1

Browse files
Files changed (1) hide show
  1. constants.py +2 -0
constants.py CHANGED
@@ -32,6 +32,8 @@ XLSX_DIR = "./file//results.xlsx"
32
 
33
  LEADERBOARD_INTRODUCTION = """# 🏆 S-Eval Leaderboard
34
  ## 🔔 Updates
 
 
35
  📣 [2024/05/31]: We release 20,000 corresponding attack prompts.
36
 
37
  📣 [2024/05/23]: We publish our [paper](https://arxiv.org/abs/2405.14191) and first release 2,000 base risk prompts. You can download the benchmark from our [project](https://github.com/IS2Lab/S-Eval), the [HuggingFace Dataset](https://huggingface.co/datasets/IS2Lab/S-Eval) or the [ModelScope Dataset](https://modelscope.cn/datasets/yuanxiaohan/S-Eval/files).
 
32
 
33
  LEADERBOARD_INTRODUCTION = """# 🏆 S-Eval Leaderboard
34
  ## 🔔 Updates
35
+ 📣 [2024/06/17]: We further release 5,000 base risk prompts and 50,000 corresponding attack prompts ([Version-0.1.1](https://github.com/IS2Lab/S-Eval)). If you require automatic safety evaluations, please feel free to submit a request via [Issues](https://github.com/IS2Lab/S-Eval/issues) or contact us by [Email](mailto:[email protected]).
36
+
37
  📣 [2024/05/31]: We release 20,000 corresponding attack prompts.
38
 
39
  📣 [2024/05/23]: We publish our [paper](https://arxiv.org/abs/2405.14191) and first release 2,000 base risk prompts. You can download the benchmark from our [project](https://github.com/IS2Lab/S-Eval), the [HuggingFace Dataset](https://huggingface.co/datasets/IS2Lab/S-Eval) or the [ModelScope Dataset](https://modelscope.cn/datasets/yuanxiaohan/S-Eval/files).