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

Safety Alignment on Alpaca-65B Weak-to-strong Safety Alignment (test)

131.81HV Score

UniARM

110.9164116.3407121.765127.1893Feb 10, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
131.813.76
2026.02
120.853.52
2026.02
111.721.99