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

Pairwise preference prediction on IUB-COSINE-S unseen (test)

91.61Accuracy

PrefSQA-F

46.83858.461570.08581.7085Jun 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
91.61
2026.06
89.28
2026.06
87.89
2026.06
48.56