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

Preference Alignment on WebGPT (test)

61.24Accuracy

FedPDPO

50.434453.239756.04558.8503Mar 20, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.03
61.24
2026.03
56.43
2026.03
55.81
2026.03
55.67
2026.03
54.92
2026.03
54.12
2026.03
53.18
2026.03
52.47
2026.03
52.34
2026.03
51.58
2026.03
50.85