Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Human Preference Alignment on HH-RLHF and PKU-SafeRLHF (test)
Loading...
3.93
Quality Score
DPO-HPS
3.618
3.699
3.78
3.861
Feb 20, 2025
Quality Score
Updated 27d ago
Evaluation Results
Method
Method
Links
Quality Score
DPO-HPS
Setting=fine-tuning
2025.02
3.93
DPO-BT
Setting=fine-tuning
2025.02
3.82
DPO-PL
Setting=fine-tuning
2025.02
3.69
SFT
Setting=fine-tuning
2025.02
3.63
Feedback
Search any
task
Search any
task
