update

Author: Yuwei Yan

docs/assets/data/behavior_leaderboard.csv

@@ -1,4 +1,4 @@
 Team name,Submission Time,Preference Estimation,Review Generation,Overall Quality
 baseline,2024-12-31, 0.6879, 0.8098, 0.7489
 RankMe, 2025-01-03, 0.6823, 0.8087, 0.7455
-伸腿瞪眼丸, 2025-01-06, 0.7966, 0.8700, 0.8333
+伸腿瞪眼丸, 2025-01-06, 0.8014, 0.8021, 0.8017

docs/pages/modeling-track.html

@@ -227,6 +227,24 @@ <h3>Topic Relevance</h3>
                   <li>An embedding vector for the review text is generated using a predefined embedding model [2].</li>
                   <li><b>Metric:</b> Cosine similarity between text embeddings, measuring alignment with the real topics.</li>
               </ul>
+
+              <h3>Preference Estimation</h3>
+              <ul>
+                  <li>The preference estimation is calculated based on the star rating accuracy.</li>
+                  <li><b>Metric:</b> 1 - MAE of star ratings, indicating the deviation from actual preferences.</li>
+              </ul>
+
+              <h3>Review Generation</h3>
+              <ul>
+                  <li>The review generation is calculated based on the review metrics.</li>
+                  <li><b>Metric:</b> 1 - (Emotional Tone Error * 0.25 + Sentiment Attitude Error * 0.25 + Topic Relevance Error * 0.5), indicating the deviation from actual reviews.</li>
+              </ul>
+
+              <h3>Overall Quality</h3>
+              <ul>
+                  <li>The overall quality is calculated based on the preference estimation and review generation.</li>
+                  <li><b>Metric:</b> (Preference Estimation + Review Generation) / 2, indicating the overall quality of the simulated reviews.</li>
+              </ul>
 
               <h3>References</h3>
               <ol>