Update README.md

README.md

@@ -6,15 +6,14 @@ base_model:
 ---
 # Libra: Large Chinese-based Safeguard for AI Content
 
-**Libra Guard** 是一款面向中文大型语言模型（LLM）的安全护栏模型。Libra Guard 采用两阶段渐进式训练流程，先利用可扩展的合成样本预训练，再使用高质量真实数据进行微调，最大化利用数据并降低对人工标注的依赖。实验表明，Libra Guard 在 Libra Bench 上的表现显著优于同类开源模型（如 ShieldLM等），在多个任务上可与先进商用模型（如 GPT-4o）接近，为中文 LLM 的安全治理提供了更强的支持与评测工具。  
+**Libra-Guard** 是一款面向中文大型语言模型（LLM）的安全护栏模型。Libra-Guard 采用两阶段渐进式训练流程，先利用可扩展的合成样本预训练，再使用高质量真实数据进行微调，最大化利用数据并降低对人工标注的依赖。实验表明，Libra-Guard 在 Libra-Test 上的表现显著优于同类开源模型（如 ShieldLM等），在多个任务上可与先进商用模型（如 GPT-4o）接近，为中文 LLM 的安全治理提供了更强的支持与评测工具。  
 
-***Libra Guard** is a safeguard model for Chinese large language models (LLMs). Libra Guard adopts a two-stage progressive training process: first, it uses scalable synthetic samples for pretraining, then employs high-quality real-world data for fine-tuning, thus maximizing data utilization while reducing reliance on manual annotation. Experiments show that Libra Guard significantly outperforms similar open-source models (such as ShieldLM) on Libra Bench and is close to advanced commercial models (such as GPT-4o) in multiple tasks, providing stronger support and evaluation tools for Chinese LLM safety governance.*
+***Libra-Guard** is a safeguard model for Chinese large language models (LLMs). Libra-Guard adopts a two-stage progressive training process: first, it uses scalable synthetic samples for pretraining, then employs high-quality real-world data for fine-tuning, thus maximizing data utilization while reducing reliance on manual annotation. Experiments show that Libra-Guard significantly outperforms similar open-source models (such as ShieldLM) on Libra-Test and is close to advanced commercial models (such as GPT-4o) in multiple tasks, providing stronger support and evaluation tools for Chinese LLM safety governance.*
 
 同时，我们基于多种开源模型构建了不同参数规模的 Libra-Guard 系列模型。本仓库为Libra-Guard-Qwen-14B-Chat的仓库。  
 
 *Meanwhile, we have developed the Libra-Guard series of models in different parameter scales based on multiple open-source models. This repository is dedicated to Libra-Guard-Qwen-14B-Chat.*
 
-Paper: [Libra: Large Chinese-based Safeguard for AI Content](https://arxiv.org/abs/####).
 
 Code: [caskcsg/Libra](https://github.com/caskcsg/Libra)
 
@@ -41,9 +40,9 @@ pip install transformers==4.32.0 accelerate tiktoken einops scipy transformers_s
 ```
 
 ## 实验结果（Experiment Results）
-在 Libra Bench 的多场景评测中，Libra Guard 系列模型相较于同类开源模型（如 ShieldLM）表现更佳，并在多个任务上与先进商用模型（如 GPT-4o）相当。下表给出了 Libra-Guard-Qwen-14B-Chat 在部分核心指标上的对比：  
+在 Libra-Test 的多场景评测中，Libra-Guard 系列模型相较于同类开源模型（如 ShieldLM）表现更佳，并在多个任务上与先进商用模型（如 GPT-4o）相当。下表给出了 Libra-Guard-Qwen-14B-Chat 在部分核心指标上的对比：  
 
-*In the multi-scenario evaluation on Libra Bench, the Libra Guard series outperforms similar open-source models such as ShieldLM, and is on par with advanced commercial models like GPT-4o in multiple tasks. The table below shows a comparison of Libra-Guard-Qwen-14B-Chat on some key metrics:*
+*In the multi-scenario evaluation on Libra-Test, the Libra-Guard series outperforms similar open-source models such as ShieldLM, and is on par with advanced commercial models like GPT-4o in multiple tasks. The table below shows a comparison of Libra-Guard-Qwen-14B-Chat on some key metrics:*
 
 | 模型                               | Average | Synthesis | Safety-Prompts | BeaverTails\_30k |
 |------------------------------------|-----------|--------|----------|----------|
@@ -129,14 +128,15 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 *If you use this project in academic or research scenarios, please cite the following references:*
 
 ```bibtex
-@misc{libra_guard_qwen_14b_chat_2025,
-  title = {Libra Guard Qwen-14B-Chat: A Safeguard Model for Chinese LLMs},
-  author = {X, ... and Y, ...},
-  year = {2025},
-  url = {https://github.com/.../Libra-Guard-Qwen-14B-Chat}
+@misc{libra,
+    title = {Libra: Large Chinese-based Safeguard for AI Content},
+    url = {https://github.com/caskcsg/Libra/},
+    author= {Li, Ziyang and Yu, Huimu and Wu, Xing and Lin, Yuxuan and Liu, Dingqin and Hu, Songlin},
+    month = {January},
+    year = {2025}
 }
 ```
 
-感谢对 Libra Guard 的关注与使用，如有任何问题或建议，欢迎提交 Issue 或 Pull Request！
+感谢对 Libra-Guard 的关注与使用，如有任何问题或建议，欢迎提交 Issue 或 Pull Request！
 
-*Thank you for your interest in Libra Guard. If you have any questions or suggestions, feel free to submit an Issue or Pull Request!*
+*Thank you for your interest in Libra-Guard. If you have any questions or suggestions, feel free to submit an Issue or Pull Request!*