fix: update text

app.py

@@ -194,7 +194,7 @@ with gr.Blocks() as demo:
                 elem_id="leaderboard-table",
             )
             
-        with gr.TabItem("🏅 Multiple Choice", elem_id="od-benchmark-tab-table", id=5):
+        with gr.TabItem("🏅 Perplexity", elem_id="od-benchmark-tab-table", id=5):
             dataframe_all_per = gr.components.Dataframe(
                 elem_id="leaderboard-table",
             )

assets/text.py

@@ -6,10 +6,12 @@ On this leaderboard, we share the evaluation results of LLMs obtained by develop
 
 # Dataset
 <span style="font-size:16px; font-family: 'Times New Roman', serif"> 
-To evaluate the conformity of large language models, we present ChineseSafe, a content moderation benchmark for Chinese (Mandarin). 
-In this benchmark, we include 4 common types of safety issues: Crime, Ethic, Mental health, and their Variant/Homophonic words. 
-In particular, the benchmark is constructed as a balanced dataset, containing safe and unsafe data collected from internet resources and public datasets [1,2,3].
-We hope the evaluation can provide a reference for researchers and engineers to build safe LLMs in Chinese. <br>  
+To evaluate the safety risk of LLMs of large language models, we present ChineseSafe,  a Chinese safety benchmark to facilitate research 
+on the content safety of large language models for Chinese (Mandarin). 
+To align with the regulations for Chinese Internet content moderation, our ChineseSafe contains 205,034 examples
+across 4 classes and 10 sub-classes of safety issues. For Chinese contexts, we add several special types of illegal content: political sensitivity, pornography,
+and variant/homophonic words. In particular, the benchmark is constructed as a balanced dataset, containing safe and unsafe data collected from internet resources and public datasets [1,2,3].
+We hope the evaluation can provides a guideline for developers and researchers to facilitate the safety of LLMs. <br>  
 
 The leadboard is under construction and maintained by <a href="https://hongxin001.github.io/" target="_blank">Hongxin Wei's</a> research group at SUSTech.
 We will release the technical report in the near future.
@@ -30,7 +32,7 @@ where <b>std</b> indicates the standard deviation of the results obtained from d
 EVALUTION_TEXT= """
 # Evaluation
 <span style="font-size:16px; font-family: 'Times New Roman', serif">
-We evaluate the models using two methods: multiple choice (perplexity) and generation. 
+We evaluate the models using two methods: perplexity(multiple choice) and generation. 
 For perplexity, we select the label which is the lowest perplexity as the predicted results. 
 For generation, we use the content generated by the model to make prediction.
 The following are the results of the evaluation. 👇👇👇    
@@ -48,16 +50,21 @@ REFERENCE_TEXT = """
 
 """
 
+# ACKNOWLEDGEMENTS_TEXT = """
+# # Acknowledgements  
+# <span style="font-size:16px; font-family: 'Times New Roman', serif">
+# This research is supported by "Data+AI" Data Intelligent Laboratory, 
+# a joint lab constructed by Deepexi and Department of Statistics and Data Science at SUSTech.
+# We gratefully acknowledge the contributions of  Prof. Bingyi Jing, Prof. Lili Yang,  
+# and Asst. Prof.Guanhua Chen for their support throughout this project.
+# """
+
 ACKNOWLEDGEMENTS_TEXT = """
-# Acknowledgements  
-<span style="font-size:16px; font-family: 'Times New Roman', serif">
-This research is supported by "Data+AI" Data Intelligent Laboratory, 
-a joint lab constructed by Deepexi and Department of Statistics and Data Science at SUSTech.
-We gratefully acknowledge the contributions of  Prof. Bingyi Jing, Prof. Lili Yang,  
-and Asst. Prof.Guanhua Chen for their support throughout this project.
+This research is supported by the Shenzhen Fundamental Research Program (Grant No.
+JCYJ20230807091809020). We gratefully acknowledge the support of "Data+AI" Data Intelligent Laboratory, a joint lab constructed by Deepexi and the Department of Statistics and Data Science
+at Southern University of Science and Technology.
 """
 
-
 CONTACT_TEXT = """
 # Contact
 <span style="font-size:16px; font-family: 'Times New Roman', serif">