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

Direct Preference Optimization on WebGPT

58.92Accuracy

FedPDPO

47.490450.457753.42556.3923Mar 20, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.03
58.92
2026.03
55.38
2026.03
54.96
2026.03
54.58
2026.03
53.96
2026.03
52.92
2026.03
50.12
2026.03
49.84
2026.03
49.01
2026.03
48.76
2026.03
47.93