Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Add "How are Faithfulness and Factuality calculated?" to FAQ
Browse files- src/display/about.py +10 -3
src/display/about.py
CHANGED
@@ -117,12 +117,19 @@ If there is no icon, we have not uploaded the information on the model yet, feel
|
|
117 |
FAQ_TEXT = """
|
118 |
---------------------------
|
119 |
# FAQ
|
120 |
-
##
|
121 |
XXX
|
122 |
-
|
|
|
123 |
XXX
|
124 |
-
|
|
|
125 |
XXX
|
|
|
|
|
|
|
|
|
|
|
126 |
"""
|
127 |
|
128 |
EVALUATION_QUEUE_TEXT = """
|
|
|
117 |
FAQ_TEXT = """
|
118 |
---------------------------
|
119 |
# FAQ
|
120 |
+
## Submitting a model
|
121 |
XXX
|
122 |
+
|
123 |
+
## Model results
|
124 |
XXX
|
125 |
+
|
126 |
+
## Editing a submission
|
127 |
XXX
|
128 |
+
|
129 |
+
## How are Faithfulness and Factuality calculated?
|
130 |
+
We classify each task into Faithfulness and Factuality tasks based on their characteristics, and calculate the Faithfulness and Factuality scores by **averaging the evaluation metrics for tasks within each category**.
|
131 |
+
We are also planning to try normalising the score for each task before averaging.
|
132 |
+
Detailed information such as how we classified the tasks and more can be found in <a href="https://arxiv.org/abs/2404.05904" target="_blank">our paper</a>.
|
133 |
"""
|
134 |
|
135 |
EVALUATION_QUEUE_TEXT = """
|