List your company

Combined Win Rate Evaluation on PKU-SafeRLHF Random prompts n = 100 samples

37.1CVaR(0.125) Combined Win RateIPO Entropic τ=10
1.11610.45819.829.142May 11, 2026

Evaluation results

MethodLinks
IPO Entropic τ=10tau (τ)=10, objective=Entropic2026.0537.1
EG Entropic τ=5tau (τ)=5, objective=Entropic2026.0536.8
IPO CVaR α=0.25alpha (α)=0.25, objective=CVaR2026.0536.8
IPO Entropic τ=5tau (τ)=5, objective=Entropic2026.0530.8
IPO CVaR α=0.125alpha (α)=0.125, objective=CVaR2026.0530.8
EG k = 1 Neutralk=1, objective=Neutral2026.0527.9
IPO k = 1 Neutralk=1, objective=Neutral2026.0527.1
NMD k = 1 Neutralk=1, objective=Neutral2026.0522.9
EGPO† (HF)source=Hugging Face2026.054.8
SFT Basetype=Baseline2026.052.5