improved dataset table

data_loader.py

@@ -659,6 +659,64 @@ METHODOLOGY = """
         width: 100%;
         padding: 2rem 0;
     }
+    
+    .dataset-table {
+        width: 100%;
+        border-collapse: separate;
+        border-spacing: 0;
+        margin: 2rem 0;
+        background: var(--bg-tertiary);
+        border-radius: 1rem;
+        overflow: hidden;
+        box-shadow: 0 4px 20px var(--shadow-color);
+    }
+
+    .dataset-table thead {
+        background: linear-gradient(90deg, var(--accent-blue), var(--accent-purple));
+    }
+
+    .dataset-table th {
+        padding: 1.25rem 1rem;
+        text-align: left;
+        color: white;
+        font-weight: 600;
+        font-size: 1rem;
+    }
+
+    .dataset-table td {
+        padding: 1rem;
+        border-bottom: 1px solid var(--border-primary);
+        color: var(--text-secondary);
+        transition: all 0.2s ease;
+    }
+
+    .dataset-table tbody tr:hover td {
+        background: var(--card-hover-bg);
+        color: var(--text-primary);
+    }
+
+    .dataset-table td[rowspan] {
+        background: var(--bg-secondary);
+        color: var(--accent-blue);
+        font-weight: 600;
+        border-right: 1px solid var(--border-primary);
+    }
+
+    .purpose-cell {
+        max-width: 300px;
+        line-height: 1.5;
+    }
+
+    .category-cell {
+        color: var(--accent-purple);
+        font-weight: 500;
+    }
+
+    .dataset-name {
+        font-family: monospace;
+        color: var(--accent-pink);
+        font-size: 0.9rem;
+    }
 
     [Rest of the CSS remains the same]
 </style>
@@ -698,64 +756,63 @@ METHODOLOGY = """
             <tbody>
                 <tr>
                     <td rowspan="4">Single-Turn</td>
-                    <td>200</td>
-                    <td>Single Function Call</td>
-                    <td>xlam_single_tool_single_call</td>
-                    <td>Basic ability to read documentation and make single function calls</td>
+                    <td>100 + 100</td>
+                    <td class="category-cell">Single Function Call</td>
+                    <td class="dataset-name">xlam_single_tool_single_call</td>
+                    <td class="purpose-cell">Evaluates basic ability to read documentation and make single function calls</td>
                 </tr>
                 <tr>
-                    <td>250</td>
-                    <td>Multiple Function Call</td>
-                    <td>xlam_multiple_tool_multiple_call</td>
-                    <td>Parallel execution and result aggregation capabilities</td>
+                    <td>200 + 50</td>
+                    <td class="category-cell">Multiple Function Call</td>
+                    <td class="dataset-name">xlam_multiple_tool_multiple_call, xlam_single_tool_multiple_call</td>
+                    <td class="purpose-cell">Tests parallel execution and result aggregation capabilities</td>
                 </tr>
                 <tr>
                     <td>100</td>
-                    <td>Irrelevant Query</td>
-                    <td>BFCL_v3_irrelevance</td>
-                    <td>Recognition of tool mismatches with user needs</td>
+                    <td class="category-cell">Irrelevant Query</td>
+                    <td class="dataset-name">BFCL_v3_irrelevance</td>
+                    <td class="purpose-cell">Tests ability to recognize when available tools don't match user needs</td>
                 </tr>
                 <tr>
                     <td>100</td>
-                    <td>Long Context</td>
-                    <td>tau_long_context</td>
-                    <td>Extended interactions and complex instructions</td>
+                    <td class="category-cell">Long Context</td>
+                    <td class="dataset-name">tau_long_context</td>
+                    <td class="purpose-cell">Assesses handling of extended interactions and complex instructions</td>
                 </tr>
                 <tr>
                     <td rowspan="5">Multi-Turn</td>
-                    <td>80</td>
-                    <td>Single Function Call</td>
-                    <td>BFCL_v3_multi_turn_base_single_func_call</td>
-                    <td>Conversational function calling abilities</td>
+                    <td>50 + 30</td>
+                    <td class="category-cell">Single Function Call</td>
+                    <td class="dataset-name">BFCL_v3_multi_turn_base_single_func_call, toolscs_single_func_call</td>
+                    <td class="purpose-cell">Tests basic conversational function calling abilities</td>
                 </tr>
                 <tr>
                     <td>50</td>
-                    <td>Multiple Function Call</td>
-                    <td>BFCL_v3_multi_turn_base_multi_func_call</td>
-                    <td>Multiple function calls in conversation</td>
+                    <td class="category-cell">Multiple Function Call</td>
+                    <td class="dataset-name">BFCL_v3_multi_turn_base_multi_func_call</td>
+                    <td class="purpose-cell">Evaluates handling of multiple function calls in conversation</td>
                 </tr>
                 <tr>
                     <td>100</td>
-                    <td>Missing Function</td>
-                    <td>BFCL_v3_multi_turn_miss_func</td>
-                    <td>Graceful handling of unavailable tools</td>
+                    <td class="category-cell">Missing Function</td>
+                    <td class="dataset-name">BFCL_v3_multi_turn_miss_func</td>
+                    <td class="purpose-cell">Tests graceful handling of unavailable tools</td>
                 </tr>
                 <tr>
                     <td>100</td>
-                    <td>Missing Parameters</td>
-                    <td>BFCL_v3_multi_turn_miss_param</td>
-                    <td>Parameter collection and incomplete information</td>
+                    <td class="category-cell">Missing Parameters</td>
+                    <td class="dataset-name">BFCL_v3_multi_turn_miss_param</td>
+                    <td class="purpose-cell">Assesses parameter collection and handling incomplete information</td>
                 </tr>
                 <tr>
                     <td>100</td>
-                    <td>Composite</td>
-                    <td>BFCL_v3_multi_turn_composite</td>
-                    <td>Overall robustness in complex scenarios</td>
+                    <td class="category-cell">Composite</td>
+                    <td class="dataset-name">BFCL_v3_multi_turn_composite</td>
+                    <td class="purpose-cell">Tests overall robustness in complex scenarios</td>
                 </tr>
             </tbody>
         </table>
     </div>
-</div>
 
 <!-- Features Grid Section -->
 <div class="features-grid">