Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Preference Optimization on Alpaca-GPT4 (Expertise)
Loading...
76.97
Win Rate
DPO
76.0652
76.3001
76.535
76.7699
Jun 5, 2025
Win Rate
PPA (alpha)
Updated 3mo ago
Evaluation Results
Method
Method
Links
Win Rate
PPA (alpha)
DPO
Backbone=Qwen2.5-3B-In...
2025.06
76.97
13.21
F-beta
beta (β)=10^0, Backbon...
2025.06
76.36
12.73
F-beta
beta (β)=10^-2, Backbo...
2025.06
76.34
13.92
F-beta
beta (β)=0, Backbone=Q...
2025.06
76.13
14.28
F-beta
beta (β)=10^-4, Backbo...
2025.06
76.1
14.18
Feedback
Search any
task
Search any
task
