Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Explanation Faithfulness on Jailbreaking DAN (test)
Loading...
24
Label Change Rate
ICL
21.56
38.03
54.5
70.97
Mar 31, 2026
Label Change Rate
Updated 18d ago
Evaluation Results
Method
Method
Links
Label Change Rate
ICL
Deletion Ratio=10%
2026.03
24
ICL
Deletion Ratio=20%
2026.03
27
Shapley
Deletion Ratio=10%
2026.03
33
Shapley
Deletion Ratio=20%
2026.03
33
LIME
Deletion Ratio=20%
2026.03
38
LIME
Deletion Ratio=10%
2026.03
54
EnsembleSHAP
Deletion Ratio=20%
2026.03
74
EnsembleSHAP
Deletion Ratio=10%
2026.03
85
Feedback
Search any
task
Search any
task