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

Hallucination Detection on Company

0.93AUC-ROC

Latent Debate Detector

0.47240.59120.710.8288May 30, 2025Jun 29, 2025Jul 30, 2025Aug 30, 2025Sep 30, 2025Oct 31, 2025Dec 1, 2025
Updated 3d ago

Evaluation Results

MethodLinks
2025.12
0.93
2025.12
0.88
2025.05
0.798
2025.05
0.784
2025.05
0.753
2025.05
0.738
2025.05
0.736
2025.05
0.729
2025.05
0.728
2025.05
0.728
2025.05
0.723
2025.12
0.72
2025.12
0.72
2025.05
0.714
2025.05
0.713
2025.12
0.71
2025.05
0.705
2025.05
0.698
2025.05
0.682
2025.05
0.678
2025.05
0.672
2025.05
0.669
2025.12
0.66
2025.05
0.659
2025.05
0.659
2025.05
0.653
2025.05
0.648
2025.05
0.644
2025.12
0.64
2025.05
0.639
2025.05
0.635
2025.05
0.632
2025.05
0.624
2025.05
0.612
2025.05
0.607
2025.05
0.603
2025.05
0.602
2025.05
0.601
2025.05
0.597
2025.05
0.593
2025.05
0.593
2025.05
0.592
2025.05
0.59
2025.05
0.582
2025.05
0.58
2025.05
0.564
2025.05
0.564
2025.05
0.562
2025.05
0.559
2025.05
0.556
2025.05
0.553
2025.05
0.542
2025.05
0.541
2025.05
0.541
2025.05
0.54
2025.05
0.54
2025.05
0.538
2025.05
0.533
2025.05
0.532
2025.05
0.53
2025.05
0.525
2025.05
0.524
2025.05
0.515
2025.05
0.514
2025.05
0.51
2025.05
0.506
2025.05
0.491
2025.12
0.49