Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Machine Unlearning on Forget Set (5%)
Loading...
44.4
Classification Accuracy
Vanilla
33.22
36.1225
39.025
41.9275
Feb 21, 2025
Classification Accuracy
ROUGE Score
Factuality Score
Cloze Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Classification Accuracy
ROUGE Score
Factuality Score
Cloze Accuracy
Vanilla
Base Model=LLaVA-13B,...
2025.02
44.4
0.604
6.1
21.9
Prompting
Base Model=LLaVA-13B,...
2025.02
42.99
0.588
5.36
20.8
KL Minim.
Base Model=LLaVA-13B,...
2025.02
38.64
0.561
4.17
19.97
NPO
Base Model=LLaVA-13B,...
2025.02
35.12
0.473
3.41
18.77
Grad. Diff
Base Model=LLaVA-13B,...
2025.02
34.16
0.435
3.95
15.55
GA
Base Model=LLaVA-13B,...
2025.02
34.04
0.423
2.98
15.19
MANU
Base Model=LLaVA-13B,...
2025.02
33.65
0.434
3.13
15.33
Feedback
Search any
task
Search any
task
