Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Defense on Q-LatHarmful
Loading...
6.52
ASR
Qwen-2.5-7B-Instruct
2.9112
27.2706
51.63
75.9894
May 27, 2026
ASR
HS
Updated 6d ago
Evaluation Results
Method
Method
Links
ASR
HS
Qwen-2.5-7B-Instruct
Backbone=Qwen-2.5-7B-I...
2026.05
6.52
1.22
SPARD
Backbone=Qwen-2.5-7B-I...
2026.05
7.33
1.29
Lisa
Backbone=Qwen-2.5-7B-I...
2026.05
8.55
1.25
SafeGrad
Backbone=Qwen-2.5-7B-I...
2026.05
27
1.77
PTST
Backbone=Qwen-2.5-7B-I...
2026.05
83.5
4.11
SafeInstr
Backbone=Qwen-2.5-7B-I...
2026.05
85.74
4.34
SFT
Backbone=Qwen-2.5-7B-I...
2026.05
96.74
4.8
Feedback
Search any
task
Search any
task