Improve model card: add metadata, library name and link to code

README.md

@@ -1,13 +1,20 @@
 ---
-license: apache-2.0
 base_model:
 - Qwen/Qwen3-4B-Instruct-2507
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- medical
+- healthcare
+- alignment
 ---
+
 # ClinAlign
 **ClinAlign** is a clinician-grounded healthcare alignment framework that scales from **instance rubrics** to a reusable library of **clinical principles**, enabling robust preference alignment and inference-time self-revision for medical LLMs.
 
 <p align="center">
-  📃 <a href="https://arxiv.org/abs/2602.09653" target="_blank">Paper</a> 
+  📃 <a href="https://arxiv.org/abs/2602.09653" target="_blank">Paper</a> • 💻 <a href="https://github.com/AQ-MedAI/ClinAlign" target="_blank">Code</a>
 </p>
 
 <p align="center">
@@ -35,8 +42,17 @@ base_model:
 
 ---
 
-   
-   
+## Citation
+
+```bibtex
+@article{lyu2025clinalign,
+  title={ClinAlign: Scaling Healthcare Alignment from Clinician Preference},
+  author={Lyu, Shiwei and Wang, Xidong and Liu, Lei and Zhu, Hao and Zhang, Chaohe and Wang, Jian and Gu, Jinjie and Wang, Benyou and Shen, Yue},
+  journal={arXiv preprint arXiv:2602.09653},
+  year={2025}
+}
+```
+
 ## Acknowledgement 
 - [verl](https://github.com/volcengine/verl)
 - [simple-evals](https://github.com/openai/simple-evals)