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

Hallucination Detection on CoQA (AUROC)

84.92AUROC

Curvature

-2.81835219.95987442.738165.516326May 25, 2026May 26, 2026May 27, 2026May 28, 2026May 29, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.05
84.92
2026.05
84.66
2026.05
82.83
2026.05
82.83
2026.05
77.43
2026.05
74.75
2026.05
73.91
2026.05
73.91
2026.05
73.91
2026.05
72
2026.05
71.23
2026.05
70.92
2026.05
70.9
2026.05
70.71
2026.05
68.6
2026.05
67.8
2026.05
67.09
2026.05
67.09
2026.05
67.05
2026.05
67.05
2026.05
67.05
2026.05
66.99
2026.05
65.98
2026.05
65.28
2026.05
63.69
2026.05
63.23
2026.05
62.26
2026.05
59.93
2026.05
59.81
2026.05
58.33
2026.05
57.81
2026.05
57.77
2026.05
57.69
2026.05
56.21
2026.05
52.74
2026.05
52.47
2026.05
52.4
2026.05
51.16
2026.05
50.59
2026.05
50.03
2026.05
0.8621
2026.05
0.8581
2026.05
0.8581
2026.05
0.8557
2026.05
0.8501
2026.05
0.8474
2026.05
0.8474
2026.05
0.843
2026.05
0.8346
2026.05
0.8159
2026.05
0.792
2026.05
0.7903
2026.05
0.7902
2026.05
0.7746
2026.05
0.7641
2026.05
0.7602
2026.05
0.7532
2026.05
0.7495
2026.05
0.7453
2026.05
0.7443
2026.05
0.7396
2026.05
0.739
2026.05
0.7362
2026.05
0.7333
2026.05
0.7315
2026.05
0.73
2026.05
0.729
2026.05
0.7264
2026.05
0.7259
2026.05
0.7206
2026.05
0.7167
2026.05
0.7124
2026.05
0.7087
2026.05
0.7086
2026.05
0.7081
2026.05
0.702
2026.05
0.7015
2026.05
0.7012
2026.05
0.694
2026.05
0.6925
2026.05
0.6925
2026.05
0.6895
2026.05
0.6877
2026.05
0.6845
2026.05
0.6791
2026.05
0.6728
2026.05
0.6633
2026.05
0.6583
2026.05
0.6562
2026.05
0.6558
2026.05
0.6532
2026.05
0.6478
2026.05
0.6407
2026.05
0.6347
2026.05
0.6276
2026.05
0.6236
2026.05
0.6187
2026.05
0.5986
2026.05
0.5772
2026.05
0.5562
Showing 100 of 108 rows