Update README.md

README.md

@@ -73,9 +73,9 @@ datasets:
 
   - **Enhanced Explainability** : Employs a structured analysis process that improves decision transparency and provides clearer insights into safety assessments.
 
-  - **Robust Generalization** : Demonstrates competitive performance in traditional QA Moderation tasks despite being trained exclusively on a 7K-sample QT dataset.
+  - **Robust Generalization** :  Notably, despite being trained on our 7K QT dataset only, ***ReasoningShield*** also demonstrates competitive performance in Question-Answer (QA) moderation on traditional benchmarks, rivaling baselines trained on datasets 10 times larger, aligning with **less is more** principle.
 
-  - **Efficient Design** : Built on compact 1B/3B base models, requiring only **2.30 GB/5.98 GB** GPU memory during inference, facilitating cost-effective deployment on resource-constrained devices.
+  - **Efficient Design** : Built on compact 1B/3B base models, it requires only **2.30 GB/5.98 GB** GPU memory during inference, facilitating cost-effective deployment on resource-constrained devices.
 
 - **Base Model**:  https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct & https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct
 
@@ -92,6 +92,8 @@ datasets:
 
 - The model is trained on a high-quality dataset of  7,000 QT pairs, please refer to the following link for detailed information:
 
+  - https://huggingface.co/datasets/ReasoningShield/ReasoningShield-Dataset
+  - 
 
 - **Risk Categories** :