Update README.md

README.md

@@ -113,6 +113,8 @@ MURI-101 is a multilingual instruction-following model, fine-tuned using a subse
 
 This model was trained on a dataset with multilingual reverse instructions, ensuring that outputs are culturally and linguistically appropriate for the target language, thus reducing translation artifacts.
 
+[Paper](https://arxiv.org/abs/2409.12958)
+
 ### Model Architecture
 - **Base Model**: mT5-XXL
 - **Training Data**: Subset of MURI-IT
@@ -195,7 +197,17 @@ muri("""این مقاله را خلاصه کنید
 
 Thanks to [Google's TRC program](https://sites.research.google/trc/about/) for supporting the training of this model.
 
-Check out [the paper](soon) for more detailed information on the experiments and results.
+Check out [the paper](https://arxiv.org/abs/2409.12958) for more detailed information on the experiments and results.
 
 ## Citation
-[PLACEHOLDER]
+```
+@misc{koksal2024muri,
+      title={MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions}, 
+      author={Abdullatif Köksal and Marion Thaler and Ayyoob Imani and Ahmet Üstün and Anna Korhonen and Hinrich Schütze},
+      year={2024},
+      eprint={2409.12958},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2409.12958}, 
+}
+```