Update README.md

README.md

@@ -5,7 +5,7 @@ language:
 - zh
 ---
 ## Introduction
-The ShieldLM model ([paper link](xxx)) initialized from [Qwen-14B-Chat](https://huggingface.co/Qwen/Qwen-14B-Chat). ShieldLM is a bilingual (Chinese and English) safety detector that mainly aims to help to detect safety issues in LLMs' generations. It aligns with general human safety standards, supports fine-grained customizable detection rules, and provides explanations for its decisions. 
+The ShieldLM model ([paper link](https://arxiv.org/abs/2402.16444)) initialized from [Qwen-14B-Chat](https://huggingface.co/Qwen/Qwen-14B-Chat). ShieldLM is a bilingual (Chinese and English) safety detector that mainly aims to help to detect safety issues in LLMs' generations. It aligns with general human safety standards, supports fine-grained customizable detection rules, and provides explanations for its decisions. 
 Refer to our [github repository](https://github.com/thu-coai/ShieldLM) for more detailed information.
 
 ## Usage
@@ -13,4 +13,4 @@ Please refer to our [github repository](https://github.com/thu-coai/ShieldLM) fo
 
 ## Performance
 ShieldLM demonstrates impressive detection performance across 4 ID and OOD test sets, compared to strong baselines such as GPT-4, Llama Guard and Perspective API.
-Refer to [our paper](xxx) for more detailed evaluation results.
+Refer to [our paper](https://arxiv.org/abs/2402.16444) for more detailed evaluation results.