Update README.md

README.md

@@ -69,4 +69,19 @@ torchrun --nproc_per_node=8 --master_port=36646 train_alignment.py \
 
 Although this project aims to better align current LMs with social norms, inappropriate content and inherent biases in the training data will still impair the alignment of the model.
 
-The model should not be used directly in any application, without a prior assessment of safety and fairness concerns specific to the application.
+The model should not be used directly in any application, without a prior assessment of safety and fairness concerns specific to the application.
+
+# Citation
+
+Please cite our paper if you use the data or code in this repo:
+
+```bibtex
+@misc{liu2023sociallyaligned,
+      title={Training Socially Aligned Language Models in Simulated Human Society},
+      author={Ruibo Liu and Ruixin Yang and Chenyan Jia and Ge Zhang and Denny Zhou and Andrew M. Dai and Diyi Yang and Soroush Vosoughi},
+      year={2023},
+      eprint={2305.16960},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```