Update README.md

README.md

@@ -31,7 +31,7 @@ Instead of learning from reference answers (as in supervised fine-tuning) or rew
 - **Outperforms RLVR and Full SFT with 20× Less Compute:** One-Shot CFT outperforms both one-shot Reinforcement Learning with Verifiable Rewards (RLVR) and full-dataset supervised fine-tuning, while requiring only 5 GPU hours on a 7B model—offering a much more efficient and stable training alternative.
 - **Robust Across Seeds and Model Scales:** One-Shot CFT remains effective across different seed problem choices and model sizes—from 1.5B to 14B parameters—demonstrating strong generalization and scalability.
 
-**This specific model is the One-Shot CFT variant trained based on [Qwen2.5-7B-Math](https://huggingface.co/Qwen/Qwen2.5-Math-7B) with DSR-CFT-p0 dataset.**
+**This specific model is the One-Shot CFT variant trained based on [Qwen2.5-7B-Math](https://huggingface.co/Qwen/Qwen2.5-Math-7B) with [DSR-CFT-p0](https://huggingface.co/datasets/TIGER-Lab/One-Shot-CFT-Data) dataset.**
 
 
 ## Main Results
@@ -53,5 +53,10 @@ Across both domains, CFT with a single problem significantly outperforms standar
 If you find our work helpful, please cite it as:
 
 ```bibtex
-
+@article{wang2025critique,
+  title={Critique fine-tuning: Learning to critique is more effective than learning to imitate},
+  author={Wang, Yubo and Yue, Xiang and Chen, Wenhu},
+  journal={arXiv preprint arXiv:2501.17703},
+  year={2025}
+}
 ```