Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Preference Learning on Toy dataset 50% label noise (test)

75.7Accuracy

SSPO

52.50858.52964.5570.571Oct 28, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.10
75.7
2025.10
75.7
2025.10
65.6
2025.10
65.6
2025.10
59.4
2025.10
59.4
2025.10
59.4
2025.10
59.4
2025.10
58.6
2025.10
58.6
2025.10
57.1
2025.10
57.1
2025.10
56.7
2025.10
56.7
2025.10
56.3
2025.10
56.3
2025.10
56.3
2025.10
56.3
2025.10
55.4
2025.10
55.4
2025.10
54.9
2025.10
54.9
2025.10
53.4
2025.10
53.4