Update README.md

README.md

@@ -45,13 +45,13 @@ Thus it is useful for Natural Language Inference and related tasks such as Zero-
 - **Model type:** Transformer Encoder
 - **Language(s) (NLP):** Fine-tuned for Myanmar (Burmese) and English
 - **License:** MIT
-- **Finetuned from model:** mDeBERTa v3 base https://huggingface.co/microsoft/mdeberta-v3-base
-- **Paper :** Myanmar XNLI https://www.researchsquare.com/article/rs-4329843
+- **Finetuned from model:** [mDeBERTa v3 base](https://huggingface.co/microsoft/mdeberta-v3-base)
+- **Paper :** [Myanmar XNLI: Building a Dataset and Exploring Low-resource Approaches to Natural Language Inference with Myanmar](https://arxiv.org/abs/2504.09645)
 - **Demo :** A demo of Zero-shot Text Classification in Myanmar can be found on this page.
 
 ## Bias, Risks, and Limitations
 
-Please refer to the papers for original foundation model: DeBERTa https://arxiv.org/abs/2006.03654 and DeBERTaV3 https://arxiv.org/abs/2111.09543.
+Please refer to the paper on [MyXNLI](https://arxiv.org/abs/2504.09645), as well as the papers for the foundation models: [DeBERTa](https://arxiv.org/abs/2006.03654) and [DeBERTaV3](https://arxiv.org/abs/2111.09543).
 <!-- Any limitations with myXNLI ? -->
 
 ## How to Get Started with the Model