Update README.md

README.md

@@ -69,6 +69,17 @@ python -m torch.distributed.launch --nproc_per_node=${num_gpus} \
 
 If you find DeBERTa useful for your work, please cite the following paper:
 
+``` latex
+@misc{he2021debertav3,
+      title={DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing}, 
+      author={Pengcheng He and Jianfeng Gao and Weizhu Chen},
+      year={2021},
+      eprint={2111.09543},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```
+
 ``` latex
 @inproceedings{
 he2021deberta,