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

Combined Win Rate Evaluation on PKU-SafeRLHF Sev-3 (n=100)

60.9Combined Win Rate (CVaR 0.125)

IPO Entropic τ=10

-0.4615.4731.447.33May 11, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
60.9
2026.05
57.2
2026.05
57.2
2026.05
56.8
2026.05
56.5
2026.05
54.9
2026.05
54.8
2026.05
52.5
2026.05
11
2026.05
1.9