Update constants.py

constants.py

@@ -35,14 +35,21 @@ LEADERBORAD_INTRODUCTION = """# SEED-Bench Leaderboard
     Please refer to [our paper](https://arxiv.org/abs/2307.16125) for more details.
     """
 
+SUBMIT_INTRODUCTION = """# Submit Precautions
+    1. Attain json file from our [github repository](https://github.com/AILab-CVC/SEED-Bench)
+    2. If you want to revision model, please ensure 'Revision Model Name' align with what's in the leaderboard.
+    3. Please ensure for right link for each submittion. Everyone could go to model's repository thought model name in the leaderboard.
+    4. If you don't want to evaluate all dimension, not evaluated dimension performance and its corresponding average performance will set to 0.
+"""
+
 TABLE_INTRODUCTION = """In the table below, we summarize each task performance of all the models.
-        We use accurancy(%) as the primary evaluation metric for most tasks. 
+        We use accurancy(%) as the primary evaluation metric for each tasks. 
     """
 
 LEADERBORAD_INFO = """
       Based on powerful Large Language Models (LLMs), recent generative Multimodal Large Language Models (MLLMs) have gained prominence as a pivotal research area, exhibiting remarkable capability for both comprehension and generation. 
       In this work, we address the evaluation of generative comprehension in MLLMs as a preliminary step towards a comprehensive assessment of generative models, by introducing a benchmark named SEED-Bench. 
-      SEED-Bench consists of 19K multiple choice questions with accurate human annotations ($\times$6 larger than existing benchmarks), which spans 12 evaluation dimensions including the comprehension of both the image and video modality. 
+      SEED-Bench consists of 19K multiple choice questions with accurate human annotations (x6 larger than existing benchmarks), which spans 12 evaluation dimensions including the comprehension of both the image and video modality. 
       We develop an advanced pipeline for generating multiple-choice questions that target specific evaluation dimensions, integrating both automatic filtering and manual verification processes. 
       Multiple-choice questions with groundtruth options derived from human annotation enables an objective and efficient assessment of model performance, eliminating the need for human or GPT intervention during evaluation. 
       We further evaluate the performance of 18 models across all 12 dimensions, covering both the spatial and temporal understanding.