Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Machine Unlearning Evaluation on TOFU
Loading...
61.4
Model Utility
Ground Truth
-2.456
14.122
30.7
47.278
Dec 23, 2025
Model Utility
Forget Quality
Updated 1mo ago
Evaluation Results
Method
Method
Links
Model Utility
Forget Quality
Ground Truth
2025.12
61.4
100
WISE
Category=Model Editing...
2025.12
61.2
0
WISE
Category=Model Editing...
2025.12
61
0
WISE
Category=Model Editing...
2025.12
60.3
0.0001
GD
Category=Model Unlearning
2025.12
58.9
0
PO
Category=Model Unlearning
2025.12
53.8
0
IKE
Category=Model Editing...
2025.12
47.3
24.9
IKE
Category=Model Editing...
2025.12
45.2
0
IKE
Category=Model Editing...
2025.12
33.8
0
ROME
Category=Model Editing...
2025.12
15.3
12.1
KL
Category=Model Unlearning
2025.12
0
0
GA
Category=Model Unlearning
2025.12
0
0
Feedback
Search any
task
Search any
task
