Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Unlearning on TOFU (Forget05)
Loading...
0.35
Model Utility
SimNPO
-0.014
0.0805
0.175
0.2695
Aug 3, 2025
Model Utility
Extraction Strength
Forget QA Probability
Forget QA ROUGE
Privleak
Updated 4d ago
Evaluation Results
Method
Method
Links
Model Utility
Extraction Strength
Forget QA Probability
Forget QA ROUGE
Privleak
SimNPO
Run time (min)=15, Epo...
2025.08
0.35
0.05
17
33
-12
IMU
Run time (min)=17, Epo...
2025.08
0.33
0.06
9
29
-83
NPO
Run time (min)=18, Epo...
2025.08
0.28
0.05
6
21
80
GA
Run time (min)=6, Epoc...
2025.08
0
0.03
3
0
48
Feedback
Search any
task
Search any
task
