nonstopfor commited on
Commit
afe54ca
1 Parent(s): b53ace0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -5,7 +5,7 @@ language:
5
  - zh
6
  ---
7
  ## Introduction
8
- 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.
9
  Refer to our [github repository](https://github.com/thu-coai/ShieldLM) for more detailed information.
10
 
11
  ## Usage
@@ -13,4 +13,4 @@ Please refer to our [github repository](https://github.com/thu-coai/ShieldLM) fo
13
 
14
  ## Performance
15
  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.
16
- Refer to [our paper](xxx) for more detailed evaluation results.
 
5
  - zh
6
  ---
7
  ## Introduction
8
+ 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.
9
  Refer to our [github repository](https://github.com/thu-coai/ShieldLM) for more detailed information.
10
 
11
  ## Usage
 
13
 
14
  ## Performance
15
  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.
16
+ Refer to [our paper](https://arxiv.org/abs/2402.16444) for more detailed evaluation results.