Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Machine Unlearning on TOFU 1.0 (Forget Set)
Loading...
1
ROUGE-L
LLAMA2-13B-TOFU
-0.04
0.23
0.5
0.77
Oct 23, 2024
ROUGE-L
Probability
Truth Ratio
Updated 4d ago
Evaluation Results
Method
Method
Links
ROUGE-L
Probability
Truth Ratio
LLAMA2-13B-TOFU
Model Type=Base (No Un...
2024.10
1
1
46
MISTRAL-7B-TOFU
Model Type=Base (No Un...
2024.10
1
1
49
LLAMA2-7B-TOFU
Model Type=Base (No Un...
2024.10
0.99
0.99
51
δ-UNLEARNING
Base Model=LLAMA2-13B-...
2024.10
0.38
0.06
53
LoRA
Base Model=LLAMA2-13B-...
2024.10
0.03
0
50
LoRA
Base Model=LLAMA2-7B-TOFU
2024.10
0.01
0
77
CMC
Base Model=LLAMA2-7B-TOFU
2024.10
0
0
33
CMC
Base Model=LLAMA2-13B-...
2024.10
0
0
29
LoRA
Base Model=MISTRAL-7B-...
2024.10
0
0
72
CMC
Base Model=MISTRAL-7B-...
2024.10
0
0
30
Feedback
Search any
task
Search any
task