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

Hallucination Detection on SQuAD (AUROC)

0.89AUROC

ID

0.5136240.6113370.709050.806763May 25, 2026May 26, 2026May 27, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.05
0.89
2026.05
0.89
2026.05
0.8884
2026.05
0.8884
2026.05
0.887
2026.05
0.8865
2026.05
0.8784
2026.05
0.8769
2026.05
0.8769
2026.05
0.8704
2026.05
0.8679
2026.05
0.8679
2026.05
0.8679
2026.05
0.8625
2026.05
0.8613
2026.05
0.8553
2026.05
0.854
2026.05
0.8433
2026.05
0.8152
2026.05
0.8106
2026.05
0.8104
2026.05
0.7929
2026.05
0.7892
2026.05
0.7892
2026.05
0.785
2026.05
0.7811
2026.05
0.7806
2026.05
0.7633
2026.05
0.7553
2026.05
0.7548
2026.05
0.7508
2026.05
0.748
2026.05
0.7432
2026.05
0.7425
2026.05
0.735
2026.05
0.7341
2026.05
0.7316
2026.05
0.7313
2026.05
0.7305
2026.05
0.7275
2026.05
0.7275
2026.05
0.727
2026.05
0.723
2026.05
0.7169
2026.05
0.7153
2026.05
0.7132
2026.05
0.7112
2026.05
0.687
2026.05
0.678
2026.05
0.6693
2026.05
0.6616
2026.05
0.6567
2026.05
0.6564
2026.05
0.6514
2026.05
0.6476
2026.05
0.6442
2026.05
0.6442
2026.05
0.6409
2026.05
0.639
2026.05
0.6387
2026.05
0.6377
2026.05
0.6314
2026.05
0.6225
2026.05
0.6183
2026.05
0.6164
2026.05
0.613
2026.05
0.613
2026.05
0.6071
2026.05
0.5988
2026.05
0.5902
2026.05
0.5902
2026.05
0.5872
2026.05
0.5784
2026.05
0.5731
2026.05
0.5703
2026.05
0.5699
2026.05
0.5688
2026.05
0.5671
2026.05
0.5544
2026.05
0.5518
2026.05
0.53
2026.05
0.5281