Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Robustness against harmful content generation on LMSYS-MF attacks

0.81Attack Success Rate

IT

-0.00120.20940.420.6306Feb 9, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
0.81
2026.02
0.77
2026.02
0.75
2026.02
0.72
2026.02
0.71
2026.02
0.68
2026.02
0.67
2026.02
0.64
2026.02
0.61
2026.02
0.61
2026.02
0.07
2026.02
0.06
2026.02
0.05
2026.02
0.05
2026.02
0.05
2026.02
0.05
2026.02
0.04
2026.02
0.03
2026.02
0.03
2026.02
0.03