Update README.md

README.md

@@ -40,4 +40,7 @@ The following hyperparameters were used during training:
 - Transformers 4.37.2
 - Pytorch 2.2.1+cu121
 - Datasets 2.18.0
-- Tokenizers 0.15.2
+- Tokenizers 0.15.2
+- 
+### Reference and Citation
+Dammu, P. P. S., Jung, H., Singh, A., Choudhury, M., & Mitra, T. (2024). "They are uncultured": Unveiling covert harms and social threats in LLM generated conversations. arXiv. https://arxiv.org/abs/2405.05378.