Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Direct Preference Optimization on PyDPO

91.47Accuracy

FedPDPO

77.908481.429284.9588.4708Mar 20, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.03
91.47
2026.03
88.42
2026.03
87.36
2026.03
86.71
2026.03
85.53
2026.03
83.93
2026.03
83.21
2026.03
81.76
2026.03
81.09
2026.03
80.12
2026.03
78.43