evalita_llm_leaderboard

Running

rzanoli commited on Sep 15

Commit

9ef3794

1 Parent(s): 07ad260

Update figure captions with minor wording changes

Files changed (1) hide show

app.py CHANGED Viewed

@@ -201,7 +201,7 @@ def boxplot_per_task(dataframe=None, baselines=None, references=None):
         text=(
             "In tasks like TE and SA, models approach the accuracy of supervised <br>"
             "models at EVALITA (dashed black line); in NER and REL they remain lower. <br>"
-            "Dashed red lines indicate GPT-4o results on generative tasks."
         ),
         xref="paper", yref="paper",
         x=0.5, y=-0.30,

         text=(
             "In tasks like TE and SA, models approach the accuracy of supervised <br>"
             "models at EVALITA (dashed black line); in NER and REL they remain lower. <br>"
+            "Dashed red lines show GPT-4o reference results for generative tasks."
         ),
         xref="paper", yref="paper",
         x=0.5, y=-0.30,