Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Combined Win Rate Evaluation on PKU-SafeRLHF Random prompts n = 100 samples
Loading...
37.1
CVaR(0.125) Combined Win Rate
IPO Entropic τ=10
1.116
10.458
19.8
29.142
May 11, 2026
CVaR(0.125) Combined Win Rate
Updated 21d ago
Evaluation Results
Method
Method
Links
CVaR(0.125) Combined Win Rate
IPO Entropic τ=10
tau (τ)=10, objective=...
2026.05
37.1
EG Entropic τ=5
tau (τ)=5, objective=E...
2026.05
36.8
IPO CVaR α=0.25
alpha (α)=0.25, object...
2026.05
36.8
IPO Entropic τ=5
tau (τ)=5, objective=E...
2026.05
30.8
IPO CVaR α=0.125
alpha (α)=0.125, objec...
2026.05
30.8
EG k = 1 Neutral
k=1, objective=Neutral
2026.05
27.9
IPO k = 1 Neutral
k=1, objective=Neutral
2026.05
27.1
NMD k = 1 Neutral
k=1, objective=Neutral
2026.05
22.9
EGPO† (HF)
source=Hugging Face
2026.05
4.8
SFT Base
type=Baseline
2026.05
2.5
Feedback
Search any
task
Search any
task