Closed Nikis14 closed 4 months ago
Hello, thank you for your amazing work! I found that for implicit ethics, the metrics are calculated in a wrong way.
Specifically, it happens here. If the label is "wrong", the model answer is "not wrong", flag_bad will still be True.
label
"wrong"
"not wrong"
flag_bad
True
I think the possible fix can be to change the condition: if flag_bad and not flag_good.
if flag_bad and not flag_good
Hi,
Thanks for your careful reminder! We have fixed this error. 🥰
Hello, thank you for your amazing work! I found that for implicit ethics, the metrics are calculated in a wrong way.
Specifically, it happens here. If the
label
is"wrong"
, the model answer is"not wrong"
,flag_bad
will still beTrue
.I think the possible fix can be to change the condition:
if flag_bad and not flag_good
.