Hallucination Detection on TriviaQA (test)
92.23AUC-ROC
MLP Probe
Updated 3d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2025.12 | 92.23 | - | 68.91 | 92.23 | 38.86 | 44.77 | |
2026.02 | 89.01 | - | - | - | - | - | |
2026.01 | 86.97 | - | - | - | - | - | |
2025.05 | 86.3 | - | - | - | - | - | |
2025.05 | 85.9 | - | - | - | - | - | |
2026.02 | 85.2 | - | - | - | - | - | |
2025.05 | 85.1 | - | - | - | - | - | |
2025.05 | 85 | - | - | - | - | - | |
2025.05 | 85 | - | - | - | - | - | |
2026.02 | 85 | - | - | - | - | - | |
2025.05 | 84.9 | - | - | - | - | - | |
2025.05 | 84.6 | - | - | - | - | - | |
2025.05 | 84.5 | - | - | - | - | - | |
2025.05 | 84.4 | - | - | - | - | - | |
2025.05 | 84.3 | - | - | - | - | - | |
2026.02 | 84.14 | - | - | - | - | - | |
2026.01 | 84.13 | - | - | - | - | - | |
2025.05 | 84.1 | - | - | - | - | - | |
2025.05 | 84.1 | - | - | - | - | - | |
2025.05 | 84.1 | - | - | - | - | - | |
2025.05 | 84 | - | - | - | - | - | |
2025.05 | 83.7 | - | - | - | - | - | |
2025.05 | 83.7 | - | - | - | - | - | |
2026.02 | 83.66 | - | - | - | - | - | |
2025.05 | 83.6 | - | - | - | - | - | |
2025.05 | 83.4 | - | - | - | - | - | |
2025.12 | 83.36 | - | 17.3 | 83.36 | 11.78 | 32.55 | |
2025.05 | 83.3 | - | - | - | - | - | |
2025.05 | 83.2 | - | - | - | - | - | |
2025.05 | 83.2 | - | - | - | - | - | |
2026.02 | 83.2 | - | - | - | - | - | |
2026.02 | 83 | - | - | - | - | - | |
2025.05 | 82.6 | - | - | - | - | - | |
2025.05 | 82.6 | - | - | - | - | - | |
2025.05 | 82.5 | - | - | - | - | - | |
2025.05 | 82.3 | - | - | - | - | - | |
2025.05 | 82 | - | - | - | - | - | |
2025.05 | 81.9 | - | - | - | - | - | |
2025.05 | 81.7 | - | - | - | - | - | |
2025.05 | 81.7 | - | - | - | - | - | |
2025.05 | 81.7 | - | - | - | - | - | |
2026.02 | 81.6 | - | - | - | - | - | |
2025.05 | 81.5 | - | - | - | - | - | |
2025.05 | 81.3 | - | - | - | - | - | |
2025.05 | 81.1 | - | - | - | - | - | |
2025.05 | 81.1 | - | - | - | - | - | |
2025.05 | 81.1 | - | - | - | - | - | |
2025.05 | 81.1 | - | - | - | - | - | |
2025.05 | 81 | - | - | - | - | - | |
2025.05 | 80.8 | - | - | - | - | - | |
2026.02 | 80.73 | - | - | - | - | - | |
2026.02 | 80.7 | - | - | - | - | - | |
2025.05 | 80.6 | - | - | - | - | - | |
2025.05 | 80.5 | - | - | - | - | - | |
2025.05 | 80.5 | - | - | - | - | - | |
2026.02 | 80.5 | - | - | - | - | - | |
2025.05 | 80.3 | - | - | - | - | - | |
2025.05 | 80.2 | - | - | - | - | - | |
2026.02 | 80.2 | - | - | - | - | - | |
2025.05 | 80 | - | - | - | - | - | |
2026.02 | 79.7 | - | - | - | - | - | |
2026.01 | 79.47 | - | - | - | - | - | |
2025.05 | 79.4 | - | - | - | - | - | |
2025.05 | 79.1 | - | - | - | - | - | |
2026.02 | 78.9 | - | - | - | - | - | |
2026.02 | 78.5 | - | - | - | - | - | |
2026.01 | 78.41 | - | - | - | - | - | |
2026.02 | 78.3 | - | - | - | - | - | |
2025.05 | 78.2 | - | - | - | - | - | |
2025.05 | 78.1 | - | - | - | - | - | |
2026.01 | 77.37 | - | - | - | - | - | |
2026.02 | 77.1 | - | - | - | - | - | |
2026.02 | 77 | - | - | - | - | - | |
2026.02 | 76.9 | - | - | - | - | - | |
2026.01 | 76.82 | - | - | - | - | - | |
2026.02 | 76.7 | - | - | - | - | - | |
2026.02 | 76.2 | - | - | - | - | - | |
2026.02 | 75.7 | - | - | - | - | - | |
2026.02 | 75.4 | - | - | - | - | - | |
2026.01 | 75.32 | - | - | - | - | - | |
2026.01 | 74.95 | - | - | - | - | - | |
2026.02 | 74.8 | - | - | - | - | - | |
2026.02 | 74.5 | - | - | - | - | - | |
2026.02 | 74.3 | - | - | - | - | - | |
2026.02 | 74 | - | - | - | - | - | |
2026.02 | 73.8 | - | - | - | - | - | |
2026.02 | 73.2 | - | - | - | - | - | |
2026.02 | 73.1 | - | - | - | - | - | |
2026.02 | 71.1 | - | - | - | - | - | |
2026.01 | 71.02 | - | - | - | - | - | |
2026.02 | 71 | - | - | - | - | - | |
2026.01 | 70.85 | - | - | - | - | - | |
2026.02 | 70.7 | - | - | - | - | - | |
2026.01 | 70.64 | - | - | - | - | - | |
2026.02 | 70.1 | - | - | - | - | - | |
2026.02 | 69.9 | - | - | - | - | - | |
2026.02 | 69.8 | - | - | - | - | - | |
2026.02 | 69.5 | - | - | - | - | - | |
2026.02 | 68.6 | - | - | - | - | - | |
2026.02 | 68.4 | - | - | - | - | - |
Showing 100 of 204 rows