Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Harmful Refusal on WG (test)

0ASR

Qwen2.5-14B-IT + SELF-REDTEAM

-2.21212.71927.6542.581Jun 9, 2025Aug 3, 2025Sep 28, 2025Nov 22, 2025Jan 17, 2026Mar 13, 2026May 8, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2025.06
0
2025.06
0.2
2025.06
0.3
2025.06
0.5
2025.06
1.9
2025.06
2.2
2025.06
2.2
2025.06
2.7
2025.06
6.3
2025.06
8
2025.06
9.4
2026.05
11.6
2026.05
12.2
2026.05
13.1
2025.10
13.8
2025.06
13.8
2026.05
14.6
2026.05
16.9
2025.06
16.9
2025.10
17.2
2026.05
17.8
2025.06
17.9
2025.10
18.3
2025.10
21.9
2025.10
22.3
2026.05
23.4
2025.06
23.7
2025.06
24.5
2025.10
25.1
2025.10
27.6
2026.05
27.9
2026.05
28.2
2025.06
30.3
2025.06
36.5
2025.06
47.8
2025.06
55.3