Update README.md
Browse files
README.md
CHANGED
|
@@ -33,10 +33,6 @@ MD-Judge was born to study the safety of different LLMs serving as an general ev
|
|
| 33 |
- [**Data**](https://huggingface.co/datasets/OpenSafetyLab/Salad-Data)
|
| 34 |
- [**Project Page**](https://adwardlee.github.io/salad_bench/)
|
| 35 |
|
| 36 |
-
## Model Sources
|
| 37 |
-
|
| 38 |
-
- **Repository:** [SALAD-Bench Github]()
|
| 39 |
-
- **Paper:** [SALAD-BENCH]()
|
| 40 |
## Model Performance
|
| 41 |
|
| 42 |
Compare our MD-Judge model with other methods on different public safety testsets using QA format. All the model-based methods are evaluated using the same safety proxy template.
|
|
|
|
| 33 |
- [**Data**](https://huggingface.co/datasets/OpenSafetyLab/Salad-Data)
|
| 34 |
- [**Project Page**](https://adwardlee.github.io/salad_bench/)
|
| 35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
## Model Performance
|
| 37 |
|
| 38 |
Compare our MD-Judge model with other methods on different public safety testsets using QA format. All the model-based methods are evaluated using the same safety proxy template.
|