Discriminative Hallucination Evaluation on AMBER-d (Acc, F1)
89.5F1 Score
UE-DPO
Updated 2d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 89.5 | 85.1 | |
2026.05 | 88.9 | 86.2 | |
2026.05 | 88.2 | 83.5 | |
2026.05 | 88 | 83.9 | |
2026.05 | 87 | 81.7 | |
2026.05 | 86 | 90 | |
2026.05 | 85.7 | 79.1 | |
2026.05 | 85 | 79.3 | |
2026.05 | 84.1 | 78.7 | |
2026.05 | 83.81 | 77.93 | |
2026.05 | 81.6 | - | |
2026.05 | 81.58 | 75.92 | |
2026.05 | 79.07 | 73.62 | |
2026.05 | 78.6 | 72.6 | |
2026.05 | 75.9 | 69.65 | |
2026.05 | 75.45 | 70.7 | |
2026.05 | 74.7 | 71.9 | |
2026.05 | 74.6 | 68.2 | |
2026.05 | 74.3 | 71.7 | |
2026.05 | 73.1 | 71.3 | |
2026.05 | 71.1 | 67 | |
2026.05 | 71.1 | 67.3 | |
2026.05 | 70.9 | 67.25 |