Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Preference Learning on Toy dataset Noise 30% (test)
Loading...
0.739
Accuracy
SSPO
0.59548
0.63274
0.67
0.70726
Oct 28, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
SSPO
prior=0.5, n_L=50, n_U...
2025.10
0.739
SSPO
prior=0.5, n_L=100, n_...
2025.10
0.733
SSPO
prior=0.5, n_L=10, n_U...
2025.10
0.698
DPO
n_L=100, n_U=1000
2025.10
0.682
DPO
n_L=10, n_U=1000
2025.10
0.673
SimPO
n_L=10, n_U=1000
2025.10
0.668
DPO
n_L=50, n_U=1000
2025.10
0.665
SimPO
n_L=50, n_U=1000
2025.10
0.665
ORPO
n_L=100, n_U=1000
2025.10
0.627
ORPO
n_L=50, n_U=1000
2025.10
0.617
ORPO
n_L=10, n_U=1000
2025.10
0.601
SimPO
n_L=100, n_U=1000
2025.10
0.601
Feedback
Search any
task
Search any
task
