Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Machine Unlearning on TOFU (Retain99)
Loading...
3.2
Refusal Rate
Guardrail Filter
2.612
6.581
10.55
14.519
May 26, 2026
Refusal Rate
Updated 7d ago
Evaluation Results
Method
Method
Links
Refusal Rate
Guardrail Filter
Backbone=Llama-2-7B-ch...
2026.05
3.2
ICCU
Backbone=Llama-3-8B-In...
2026.05
7.5
ICCU
Backbone=Llama-2-7B-ch...
2026.05
8
Guardrail Classifier
Backbone=Llama-3-8B-In...
2026.05
9.7
Guardrail Classifier
Backbone=Llama-2-7B-ch...
2026.05
9.7
Guardrail Filter
Backbone=Llama-3-8B-In...
2026.05
17.9
Feedback
Search any
task
Search any
task