explanation update

app.py

@@ -15,8 +15,8 @@ explanation_data = {
         "medqa_diff"
     ],
     "Description": [
-        "Model accuracy on the B4BQA task.",
-        "Average model accuracy on tasks where generic drug names are substituted with brand names.",
+        "Model accuracy on the [Come up with a fitting name] task.",
+        "[How do we best explain this?]",
         "Model accuracy on MedMCQA task where generic drug names are substituted with brand names.",
         "Model accuracy on MedMCQA task with original data. (Only includes questions that overlap with the g2b dataset)",
         "Difference in MedMCQA accuracy for swapped and non-swapped datasets, highlighting the impact of G2B drug name substitution on performance.",