Update README.md

README.md

@@ -60,4 +60,17 @@ results = encoder.encode_batch(["Jak dożyć 100 lat?", "Trzeba zdrowo się odż
 print(cos_sim(results[0], results[1]))
 ```
 
-Using SPLADE to index and search large datasets is a more complex task and requires integration with term-based index such as Lucene. For this purpose, you can use the official [SPLADE implementation](https://github.com/naver/splade) or reimplementation of this model in our [PIRB library](https://github.com/sdadas/pirb).
+Using SPLADE to index and search large datasets is a more complex task and requires integration with term-based index such as Lucene. For this purpose, you can use the official [SPLADE implementation](https://github.com/naver/splade) or reimplementation of this model in our [PIRB library](https://github.com/sdadas/pirb).
+
+## Citation
+
+```bibtex
+@article{dadas2024pirb,
+  title={{PIRB}: A Comprehensive Benchmark of Polish Dense and Hybrid Text Retrieval Methods}, 
+  author={Sławomir Dadas and Michał Perełkiewicz and Rafał Poświata},
+  year={2024},
+  eprint={2402.13350},
+  archivePrefix={arXiv},
+  primaryClass={cs.CL}
+}
+```