cjj-leaderboard

app.py

@@ -203,7 +203,7 @@ This leaderboard is used to show the performance of the <strong>automatic evalua
         ('', 'methods'),
         ('', 'overall'),
         ('Dialogue Generation', 'accuracy'),
-        ('Dialogue Generation', 'kendall\'s tau'),
+        ('Dialogue Generation', 'kendall'),
         ('Dialogue Generation', 'spearman'),
         # ('Text Expansion', 'accuracy'),
         # ('Text Expansion', 'kendall\'s tau'),
@@ -221,7 +221,7 @@ This leaderboard is used to show the performance of the <strong>automatic evalua
         ('', 'methods'): ["chatglm3-6b", "baichuan2-13b", "chatglm-pro", "gpt-4o-mini"],
         ('', 'overall'): [0,0,0,0],
         ('Dialogue Generation', 'accuracy'): [0.5806, 0.5483, 0.6001, 0.6472],
-        ('Dialogue Generation', 'kendall\'s tau'): [0.3243, 0.1739, 0.3042, 0.4167],
+        ('Dialogue Generation', 'kendall'): [0.3243, 0.1739, 0.3042, 0.4167],
         ('Dialogue Generation', 'spearman'): [0.3505, 0.1857, 0.3264, 0.4512],
         # ('Text Expansion', 'accuracy'): [0.5107, 0.5050, 0.5461, 0.5581],
         # ('Text Expansion', 'kendall\'s tau'): [0.1281, 0.0635, 0.2716, 0.3864],