fontSize

app.py

@@ -142,55 +142,51 @@ elif page == "Methodology":
     st.header("Methodology")
     st.image("asserts/method.svg", use_column_width=True)
     st.markdown("""
-<ol class='main-text'>
-  <li class='main-text'>First, we choose four subtasks as shown in the table below:</li>
-  <table class='main-text'>
-    <thead>
-      <tr>
-        <th style="text-align: left">Task</th>
-        <th style="text-align: left">Description</th>
-        <th style="text-align: left">Dataset</th>
-      </tr>
-    </thead>
-    <tbody>
-      <tr>
-        <td style="text-align: left">Summary Generation (SG)</td>
-        <td style="text-align: left">write a summary for the specified text</td>
-        <td style="text-align: left">XSum: over 226k news articles</td>
-      </tr>
-      <tr>
-        <td style="text-align: left">Non-Factoid QA (NFQA)</td>
-        <td style="text-align: left">construct long-form answers to open-ended non-factoid questions</td>
-        <td style="text-align: left">NF_CATS: 12k non-factoid questions</td>
-      </tr>
-      <tr>
-        <td style="text-align: left">Text Expansion (TE)</td>
-        <td style="text-align: left">given a theme, participants need to generate stories related to the theme</td>
-        <td style="text-align: left">WritingPrompts: 303k story themes2</td>
-      </tr>
-      <tr>
-        <td style="text-align: left">Dialogue Generation (DG)</td>
-        <td style="text-align: left">generate human-like responses to numerous topics in daily conversation contexts</td>
-        <td style="text-align: left">DailyDialog: 13k daily conversation contexts</td>
-      </tr>
-    </tbody>
-  </table>
-  <li class='main-text'>Second, we choose a series of popular LLMs during the competition to generate answers.</li>
-  <li class='main-text'>Third, we manually annotate the answer sets for each question, which will be used as gold standards for evaluating the performance of different evaluation methods.</li>
-  <li class='main-text'>Last, we will collect evaluation results from participants and calculate consistency with manually annotated results. We will use Accuracy, Kendall’s tau and Spearman correlation coefficient as the evaluation metrics.</li>
-</ol>
+<p class='main-text'>First, we choose four subtasks as shown in the table below:</p>
+<table class='main-text'>
+<thead>
+    <tr>
+    <th style="text-align: left">Task</th>
+    <th style="text-align: left">Description</th>
+    <th style="text-align: left">Dataset</th>
+    </tr>
+</thead>
+<tbody>
+    <tr>
+    <td style="text-align: left">Summary Generation (SG)</td>
+    <td style="text-align: left">write a summary for the specified text</td>
+    <td style="text-align: left">XSum: over 226k news articles</td>
+    </tr>
+    <tr>
+    <td style="text-align: left">Non-Factoid QA (NFQA)</td>
+    <td style="text-align: left">construct long-form answers to open-ended non-factoid questions</td>
+    <td style="text-align: left">NF_CATS: 12k non-factoid questions</td>
+    </tr>
+    <tr>
+    <td style="text-align: left">Text Expansion (TE)</td>
+    <td style="text-align: left">given a theme, participants need to generate stories related to the theme</td>
+    <td style="text-align: left">WritingPrompts: 303k story themes2</td>
+    </tr>
+    <tr>
+    <td style="text-align: left">Dialogue Generation (DG)</td>
+    <td style="text-align: left">generate human-like responses to numerous topics in daily conversation contexts</td>
+    <td style="text-align: left">DailyDialog: 13k daily conversation contexts</td>
+    </tr>
+</tbody>
+</table>
+<p class='main-text'>Second, we choose a series of popular LLMs during the competition to generate answers.</p>
+<p class='main-text'>Third, we manually annotate the answer sets for each question, which will be used as gold standards for evaluating the performance of different evaluation methods.</p>
+<p class='main-text'>Last, we will collect evaluation results from participants and calculate consistency with manually annotated results. We will use Accuracy, Kendall’s tau and Spearman correlation coefficient as the evaluation metrics.</p>
     """,unsafe_allow_html=True)
 
 elif page == "Datasets":
     st.header("Datasets")
     st.markdown("""
 <p class='main-text'>A brief description of the specific dataset we used, along with the original download link, is provided below:</p>
-<ul class='main-text'>
-  <li class='main-text'><strong>Summary Generation (SG): <a href="https://huggingface.co/datasets/EdinburghNLP/xsum">Xsum</a></strong>: A real-world single document news summary dataset collected from online articles by the British Broadcasting Corporation (BBC) and contains over 220 thousand news documents.</li>
-  <li class='main-text'><strong>Non-Factoid QA (NFQA): <a href="https://github.com/Lurunchik/NF-CATS">NF_CATS</a></strong>: A dataset contains examples of 12k natural questions divided into eight categories.</li>
-  <li class='main-text'><strong>Text Expansion (TE): <a href="https://huggingface.co/datasets/euclaise/writingprompts">WritingPrompts</a></strong>: A large dataset of 300K human-written stories paired with writing prompts from an online forum.</li>
-  <li class='main-text'><strong>Dialogue Generation (DG): <a href="https://huggingface.co/datasets/daily_dialog">DailyDialog</a></strong>: A high-quality dataset of 13k multi-turn dialogues. The language is human-written and less noisy.</li>
-</ul>
+<p class='main-text'>1. <strong>Summary Generation (SG): <a href="https://huggingface.co/datasets/EdinburghNLP/xsum">Xsum</a></strong>: A real-world single document news summary dataset collected from online articles by the British Broadcasting Corporation (BBC) and contains over 220 thousand news documents.</p>
+<p class='main-text'>2. <strong>Non-Factoid QA (NFQA): <a href="https://github.com/Lurunchik/NF-CATS">NF_CATS</a></strong>: A dataset contains examples of 12k natural questions divided into eight categories.</p>
+<p class='main-text'>3. <strong>Text Expansion (TE): <a href="https://huggingface.co/datasets/euclaise/writingprompts">WritingPrompts</a></strong>: A large dataset of 300K human-written stories paired with writing prompts from an online forum.</p>
+<p class='main-text'>4. <strong>Dialogue Generation (DG): <a href="https://huggingface.co/datasets/daily_dialog">DailyDialog</a></strong>: A high-quality dataset of 13k multi-turn dialogues. The language is human-written and less noisy.</p>
 <p class='main-text'>For your convenience, we have released <strong>the training set</strong> (with human-annotated results) and <strong>the test set</strong> (without human-annotated results) on <a href="https://huggingface.co/datasets/THUIR/AEOLLM">https://huggingface.co/datasets/THUIR/AEOLLM</a>, which you can easily download.</p>
     """,unsafe_allow_html=True)
 
@@ -230,13 +226,11 @@ elif page == "Data and File format":
     st.markdown("""
 <p class='main-text'>We will be following a similar format as the ones used by most <strong>TREC submissions</strong>, which is repeated below. White space is used to separate columns. The width of the columns in the format is not important, but it is important to have exactly five columns per line with at least one space between the columns.</p>
 <p class='main-text'><strong>taskId  questionId  answerId  score  rank</strong></p>
-<ol class='main-text'>
-  <li class='main-text'>the first column is the taskeId (index different tasks)</li>
-  <li class='main-text'>the second column is questionId (index different questions in the same task)</li>
-  <li class='main-text'>the third column is answerId (index the answer provided by different LLMs to the same question)</li>
-  <li class='main-text'>the fourth column is score (index the score to the answer given by participants)</li>
-  <li class='main-text'>the fifth column is rank (index the rank of the answer within all answers to the same question)</li>
-</ol>
+<p class='main-text'>1. the first column is the taskeId (index different tasks)</p>
+<p class='main-text'>2. the second column is questionId (index different questions in the same task)</p>
+<p class='main-text'>3. the third column is answerId (index the answer provided by different LLMs to the same question)</p>
+<p class='main-text'>4. the fourth column is score (index the score to the answer given by participants)</p>
+<p class='main-text'>5. the fifth column is rank (index the rank of the answer within all answers to the same question)</p>
     """,unsafe_allow_html=True)
 elif page == "Submit":
     st.header("Submit")
@@ -248,13 +242,11 @@ elif page == "LeaderBoard":
     # # 描述
     st.markdown("""
 <div class='main-text'>
-This leaderboard is used to show the performance of the <strong>automatic evaluation methods of LLMs</strong> submitted by the <strong>AEOLLM team</strong> on four tasks:
-<ul class='main-text'>       
-<li class='main-text'>Dialogue Generation (DG)</li>
-<li class='main-text'>Text Expansion (TE)</li>
-<li class='main-text'>Summary Generation (SG)</li>
-<li class='main-text'>Non-Factoid QA (NFQA)</li>
-</ul>
+This leaderboard is used to show the performance of the <strong>automatic evaluation methods of LLMs</strong> submitted by the <strong>AEOLLM team</strong> on four tasks:    
+<p class='main-text'>1. Dialogue Generation (DG)</p>
+<p class='main-text'>2. Text Expansion (TE)</p>
+<p class='main-text'>3. Summary Generation (SG)</p>
+<p class='main-text'>4. Non-Factoid QA (NFQA)</p>
 </div>
     """, unsafe_allow_html=True)
     # 创建示例数据