Update README.md

README.md

@@ -6,6 +6,6 @@ base_model:
 - princeton-nlp/Llama-3-Base-8B-SFT
 ---
 
-This model is fine-tuned from the princeton-nlp/Llama-3-Base-8B-SFT model using the SelectiveDPO algorithm on the Ultrafeedback_binarized dataset.
+This model is fine-tuned from the princeton-nlp/Llama-3-Base-8B-SFT model using the [SelectiveDPO](https://huggingface.co/papers/2502.09650) on the Ultrafeedback_binarized dataset.
 
 For the recipe to reproduce this model, please visit our [GitHub page](https://github.com/glorgao/SelectiveDPO).