Update README.md

README.md

@@ -43,11 +43,20 @@ It was fine-tuned on the CANNOT dataset's train split for 500 steps using the [f
 
 
 
-## Citation [optional]
+## Citation
 
-Please cite our INLG 2023 paper, if you use our model. 
+Please cite our [INLG 2023 paper](https://arxiv.org/abs/2307.13989), if you use our model. 
 **BibTeX:**
-tba
+```bibtex
+@misc{anschütz2023correct,
+      title={This is not correct! Negation-aware Evaluation of Language Generation Systems}, 
+      author={Miriam Anschütz and Diego Miguel Lozano and Georg Groh},
+      year={2023},
+      eprint={2307.13989},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```