Update README.md
Browse files
README.md
CHANGED
|
@@ -24,6 +24,9 @@ base_model:
|
|
| 24 |
Unlike traditional guardian models that screen for a fixed set of harms (e.g., violence or self-harm) , DynaGuard can enforce bespoke, application-specific rules. This includes scenarios like preventing a customer service bot from mistakenly issuing refunds or ensuring a medical bot avoids giving unauthorized advice.
|
| 25 |
The DynaGuard series achieves state-of-the-art performance across a wide range of safety and compliance benchmarks, with the flagship **[DynaGuard-8B](https://huggingface.co/tomg-group-umd/DynaGuard-8B)** model outperforming other guardian models and even strong generalist models like GPT-4o-mini.
|
| 26 |
|
|
|
|
|
|
|
|
|
|
| 27 |
## Model Details
|
| 28 |
|
| 29 |
* **Developed by:** University of Maryland, Capital One
|
|
|
|
| 24 |
Unlike traditional guardian models that screen for a fixed set of harms (e.g., violence or self-harm) , DynaGuard can enforce bespoke, application-specific rules. This includes scenarios like preventing a customer service bot from mistakenly issuing refunds or ensuring a medical bot avoids giving unauthorized advice.
|
| 25 |
The DynaGuard series achieves state-of-the-art performance across a wide range of safety and compliance benchmarks, with the flagship **[DynaGuard-8B](https://huggingface.co/tomg-group-umd/DynaGuard-8B)** model outperforming other guardian models and even strong generalist models like GPT-4o-mini.
|
| 26 |
|
| 27 |
+
[https://arxiv.org/abs/2509.02563](https://arxiv.org/abs/2509.02563)
|
| 28 |
+
|
| 29 |
+
|
| 30 |
## Model Details
|
| 31 |
|
| 32 |
* **Developed by:** University of Maryland, Capital One
|