considerations

datacards/considerations.py

@@ -73,10 +73,10 @@ def considerations_page():
             "considerations"
         ].get("limitations", {})
         make_text_area(
-            label="Describe any known technical limitations, such as spurrious correlations, train/test overlap, annotation biases, or mis-annotations? " + \
-            "Describe them and cite the works that first identified these limitations when possible.",
+            label="Describe any known technical limitations, such as spurrious correlations, train/test overlap, annotation biases, or mis-annotations, " + \
+            "and cite the works that first identified these limitations when possible.",
             key_list=key_pref + ["data-technical-limitations"],
-            help="",
+            help="Outline any properties of the dataset that might lead a trained model with good performance on the metric to not behave as expected.",
         )
         make_text_area(
             label="When using a model trained on this dataset in a setting where users or the public may interact with its predictions, what are some pitfalls to look out for? " + \