Update README.md

README.md

@@ -55,7 +55,7 @@ This repository provides the **OpenGuardrails-Text-2510** model — a 3.3B-param
    OpenGuardrails achieves **state-of-the-art (SOTA) performance** on multiple safety benchmarks, excelling in both **prompt** and **response classification** across **English, Chinese, and multilingual tasks**.  
    All models are released under the **Apache 2.0 License** for public use.
 
-For more details, please refer to our [Website](https://www.openguardrails.com/), [GitHub](https://github.com/openguardrails/openguardrails), and [Technical Report](https://github.com/openguardrails/openguardrails/blob/main/OpenGuardrailsTechReport.pdf).
+For more details, please refer to our [Website](https://www.openguardrails.com/), [GitHub](https://github.com/openguardrails/openguardrails), and [Technical Report](https://arxiv.org/abs/2510.19169).
 
 ![image/jpeg](https://www.openguardrails.com/performance.png)
 
@@ -162,4 +162,15 @@ Full license text: [https://www.apache.org/licenses/LICENSE-2.0](https://www.apa
 * **Website:** [https://www.openguardrails.com](https://www.openguardrails.com)
 * **GitHub:** [https://github.com/openguardrails/openguardrails](https://github.com/openguardrails/openguardrails)
 
+## Citation
 
+If you find our work helpful, feel free to give us a cite.
+
+```bibtex
+@misc{openguardrails,
+      title={OpenGuardrails: An Open-Source Context-Aware AI Guardrails Platform}, 
+      author={Thomas Wang and Haowen Li},
+      year={2025},
+      url={https://arxiv.org/abs/2510.19169}, 
+}
+```