Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Human Preference Alignment on PKU-Safety
Loading...
67.1
Win Rate
DPO-HPS
55.66
58.63
61.6
64.57
Feb 20, 2025
Win Rate
Lose Rate
Tie Rate
Updated 27d ago
Evaluation Results
Method
Method
Links
Win Rate
Lose Rate
Tie Rate
DPO-HPS
Comparison Baseline=SF...
2025.02
67.1
5.15
27.75
DPO-HPS
Comparison Baseline=DP...
2025.02
57.65
10.35
32
DPO-HPS
Comparison Baseline=DP...
2025.02
56.1
11.15
32.75
Feedback
Search any
task
Search any
task