Hallucination monitoring on Treatment domain
0.8AUROC
HalMit
Updated 19d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2025.07 | 0.8 | 0.86 | 82 | 88 | |
2025.07 | 0.79 | 0.8 | 81 | 85 | |
2025.07 | 0.76 | 0.8 | 79 | 73 | |
2025.07 | 0.75 | 0.71 | 89 | 84 | |
2025.07 | 0.74 | 0.84 | 70 | 75 | |
2025.07 | 0.73 | 0.75 | 80 | 79 | |
2025.07 | 0.72 | 0.8 | 68 | 78 | |
2025.07 | 0.71 | 0.72 | 69 | 70 | |
2025.07 | 0.69 | 0.7 | 77 | 79 | |
2025.07 | 0.68 | 0.71 | 79 | 75 | |
2025.07 | 0.68 | 0.72 | 81 | 71 | |
2025.07 | 0.64 | 0.59 | 44 | 49 | |
2025.07 | 0.6 | 0.58 | 79 | 56 | |
2025.07 | 0.59 | 0.56 | 60 | 55 | |
2025.07 | 0.58 | 0.52 | 49 | 59 | |
2025.07 | 0.57 | 0.6 | 55 | 51 | |
2025.07 | 0.56 | 0.54 | 56 | 66 | |
2025.07 | 0.56 | 0.69 | 60 | 65 | |
2025.07 | 0.56 | 0.67 | 64 | 69 | |
2025.07 | 0.52 | 0.39 | 44 | 54 | |
2025.07 | 0.49 | 0.5 | 42 | 50 | |
2025.07 | 0.48 | 0.71 | 70 | 61 | |
2025.07 | 0.43 | 0.49 | 37 | 56 | |
2025.07 | 0.39 | 0.41 | 67 | 45 |