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

Fact Verification on FEVER (val)

0.555True Deferral-Advice Loss

augmented surrogate

0.54420.61710.690.7629Mar 15, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
0.555
2026.03
0.558
2026.03
0.566
2026.03
0.58
2026.03
0.596
2026.03
0.607
2026.03
0.611
2026.03
0.613
2026.03
0.619
2026.03
0.619
2026.03
0.619
2026.03
0.619
2026.03
0.619
2026.03
0.619
2026.03
0.619
2026.03
0.619
2026.03
0.619
2026.03
0.619
2026.03
0.626
2026.03
0.633
2026.03
0.64
2026.03
0.64
2026.03
0.641
2026.03
0.647
2026.03
0.657
2026.03
0.662
2026.03
0.664
2026.03
0.671
2026.03
0.674
2026.03
0.675
2026.03
0.682
2026.03
0.69
2026.03
0.695
2026.03
0.695
2026.03
0.695
2026.03
0.695
2026.03
0.695
2026.03
0.704
2026.03
0.705
2026.03
0.711
2026.03
0.715
2026.03
0.723
2026.03
0.735
2026.03
0.76
2026.03
0.765
2026.03
0.788
2026.03
0.795
2026.03
0.825