Update README.md

README.md

@@ -24,7 +24,7 @@ base_model:
     </a> 
     <br>
     <a href="https://huggingface.co/HeAAAAA/Crab" style="margin: 0 10px;">
-      💬 <strong>Role-palying Model</strong>
+      💬 <strong>Role-playing Model</strong>
     </a>  |
     <a href="https://huggingface.co/HeAAAAA/RoleRM" style="margin: 0 10px;">
       💬 <strong>Role-palying Evaluation Model</strong>
@@ -38,8 +38,10 @@ base_model:
     </a>  |
     <a href="https://huggingface.co/datasets/HeAAAAA/Crab-manually-annotated-role-playing-evaluation-dataset" style="margin: 0 10px;">
       💬 <strong>Annotated Role-playing Evaluation Dataset</strong>
+    </a>   |
+     <a href="https://huggingface.co/datasets/HeAAAAA/Crab-human-preference" style="margin: 0 10px;">
+      💬 <strong>Human-preference Dataset</strong>
     </a>
-    
   </p>
 
 </div>
@@ -58,7 +60,8 @@ Thus, to validate RP-LLMs' effectiveness, we introduced a new benchmark containi
 Sufficient experiments reveal that RoleRM significantly outperforms ChatGPT and other evaluation methods in conducting fine-grained evaluations of RP. 
 Also, RP-LLMs powered by Crab demonstrate superior performance across various fine-grained aspects.
 
-More details can be seen at Github {https://github.com/KaiHe-better/Crab?tab=readme-ov-file}.
+More details can be seen at [GitHub](https://github.com/KaiHe-better/Crab?tab=readme-ov-file).
+
 
 
 
@@ -119,33 +122,32 @@ Table 2: The ablation study for Crab. Due to missing attributes in our dataset,
 
 <br>
 
-# 4. Three Datasets
-We publish three datasets, including Crab role-playing train set, Crab role-playing evaluation benchmark, and manually annotated role-playing evaluation dataset (can be used for training a Role-palying Evaluation Model).
-
-## 4.1 Crab role-playing train set:
-{https://huggingface.co/datasets/HeAAAAA/Crab-role-playing-train-set}
-
-## 4.2 Crab role-playing evaluation benchmark:
-{https://huggingface.co/datasets/HeAAAAA/Crab-role-playing-evaluation-benchmark}
-
-## 4.3 Crab manually annotated role-playing evaluation dataset:
-{https://huggingface.co/datasets/HeAAAAA/Crab-manually-annotated-role-playing-evaluation-dataset}
+# 4. Four Datasets
+We totally publish three datasets, including :
 
+1. [Crab role-playing train set](https://huggingface.co/datasets/HeAAAAA/Crab-role-playing-train-set) : the dataset used for fine‑tuning a role‑playing LLM.
+2. [Crab role-playing evaluation benchmark](https://huggingface.co/datasets/HeAAAAA/Crab-role-playing-evaluation-benchmark) :the dataset used for evalauating a role‑playing LLM.
+3. [Manually annotated role-playing evaluation dataset](https://huggingface.co/datasets/HeAAAAA/Crab-manually-annotated-role-playing-evaluation-dataset):  the dataset used for training a evaluator for role‑playing tasks.
+4. [Crab Human preference dataset](https://huggingface.co/datasets/HeAAAAA/Crab-Human-preference): the dataset used to train a role‑playing LLM via reinforcement learning
 
 <br>
 
 # 5. Fine-tuned Role-playing Model
-We release a fine-tuned model to achieve configurable Role-Playing tasks.
-{https://huggingface.co/HeAAAAA/Crab}
+We release a fine-tuned Role-playin LLM to achieve configurable Role-Playing tasks:
+
+[Download Link](https://huggingface.co/HeAAAAA/Crab)
 
 <br>
 
 # 6. Role-palying Evaluation Model
-We release a trained model to automate the evaluation of role-playing tasks.
-{https://huggingface.co/HeAAAAA/RoleRM}
+We release a trained LLM to automate the evaluation of role-playing tasks:
+
+[Download Link](https://huggingface.co/HeAAAAA/RoleRM)
 
 <br>
 
+
+
 # 7. Citation
 
 ```bibtex
@@ -155,7 +157,3 @@ We release a trained model to automate the evaluation of role-playing tasks.
   year={2025},
 }
 
-
-
-
-