Hallucination Detection on FOIL (Reference-Conditioned Accuracy)
98.4Accuracy (4 Refs)
Ref-FLEUR
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.12 | 98.4 | 97.3 | |
2025.12 | 98.4 | 97.8 | |
2025.12 | 97.2 | 96.5 | |
2025.12 | 97 | 96.4 | |
2025.12 | 96.8 | 96.8 | |
2025.12 | 96.7 | 96.7 | |
2025.12 | 96.1 | 95.1 | |
2025.12 | 95.4 | 93.3 | |
2023.03 | 94.9 | 93.7 | |
2025.12 | 94.9 | 93.7 | |
2025.12 | 94.3 | 94.3 | |
2023.03 | 94.1 | 85.7 | |
2025.12 | 94.1 | 93.5 | |
2025.12 | 93.6 | - | |
2023.03 | 93.5 | 90.5 | |
2025.12 | 93.1 | 93.1 | |
2023.03 | 92.6 | 91 | |
2025.12 | 92.6 | 91 | |
2025.12 | 90.6 | 82.5 | |
2025.12 | 90.2 | 90.2 | |
2023.03 | 89.9 | 89.9 | |
2025.12 | 89.9 | 89.9 | |
2023.03 | 87.2 | 87.2 | |
2025.12 | 87.2 | 87.2 | |
2023.03 | 87 | 66.2 | |
2025.12 | 86.1 | 75.5 | |
2023.03 | 85.4 | 65.7 | |
2025.12 | 82.6 | 66.5 | |
2025.12 | 82.6 | 78.8 | |
2023.03 | 82 | 70.1 | |
2025.12 | 79.3 | 71.7 | |
2023.03 | 70.4 | 54.6 |