Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Defense on LatHarmful
Loading...
7.88
ASR
Qwen-2.5-7B-Instruct
4.5184
27.2092
49.9
72.5908
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
7.88
1.23
Lisa
Backbone=Qwen-2.5-7B-I...
2026.05
7.88
1.26
SPARD
Backbone=Qwen-2.5-7B-I...
2026.05
7.88
1.31
SafeGrad
Backbone=Qwen-2.5-7B-I...
2026.05
20
1.75
SafeInstr
Backbone=Qwen-2.5-7B-I...
2026.05
76.77
3.99
PTST
Backbone=Qwen-2.5-7B-I...
2026.05
82.42
4.13
SFT
Backbone=Qwen-2.5-7B-I...
2026.05
91.92
4.6
Feedback
Search any
task
Search any
task