Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Uncertainty Estimation on Aggregate (Cola, GEmot, IMDB, News, SST5, Toxigen, YELP)
Loading...
8.4
ECE
ALIEN
7.908
11.229
14.55
17.871
May 21, 2025
ECE
Updated 11d ago
Evaluation Results
Method
Method
Links
ECE
ALIEN
Category=Probability b...
2025.05
8.4
SR
2025.05
9.4
Linear probing
Layer=Last
2025.05
9.9
Attention pooling
Layer=Last
2025.05
10.3
Linear probing
Layer=Begin
2025.05
10.5
Attention pooling
Layer=Mid
2025.05
10.5
Linear probing
Layer=Mid
2025.05
10.8
Attention pooling
Layer=Begin
2025.05
12.2
Entropy
Category=Probability b...
2025.05
12.6
MDR
Category=Mahalanobis d...
2025.05
14.9
MD
Category=Mahalanobis d...
2025.05
19.2
MDM
Category=Mahalanobis d...
2025.05
19.3
RDE
Category=Mahalanobis d...
2025.05
20.7
Feedback
Search any
task
Search any
task