Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Linguistic Acceptability on CoLA GLUE (val)
Loading...
84.76
Accuracy
MCD
68.5048
72.7249
76.945
81.1651
Jun 17, 2024
Accuracy
Expected Calibration Error
Negative Log-Likelihood
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Expected Calibration Error
Negative Log-Likelihood
MCD
Backbone=RoBERTa-base
2024.06
84.76
4.58
0.39
ENS
Backbone=RoBERTa-base
2024.06
84.08
12.44
0.62
MLE
Backbone=RoBERTa-base
2024.06
83.29
10.7
0.53
LAP
Backbone=RoBERTa-base
2024.06
83.29
3.13
0.48
MAP
Backbone=RoBERTa-base
2024.06
83
10.61
0.53
BLoB
Backbone=RoBERTa-base,...
2024.06
80.92
10.9
0.52
BLoB
Backbone=RoBERTa-base,...
2024.06
80.89
7.83
0.46
BLoB
Backbone=RoBERTa-base,...
2024.06
80.54
7.76
0.45
BBB
Backbone=RoBERTa-base
2024.06
69.13
3.9
0.62
Feedback
Search any
task
Search any
task
