Faithfulness evaluation on BoolQ
37AUC π-Soft-NS
Grad-ELLM
Updated 2d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 37 | 2.462 | |
2026.01 | 33.4 | 2.381 | |
2026.01 | 32.6 | 1.953 | |
2026.01 | 32.4 | 1.778 | |
2026.01 | 31.7 | 1.765 | |
2026.01 | 31.6 | 1.832 | |
2026.01 | 31.6 | 0.451 | |
2026.01 | 31.6 | 45.1 | |
2026.01 | 29.9 | 0.487 | |
2026.01 | 29.9 | 48.7 | |
2026.01 | 29.4 | 0.448 | |
2026.01 | 29.4 | 44.8 | |
2026.01 | 29.2 | 0.452 | |
2026.01 | 29.2 | 45.2 | |
2026.01 | 28.9 | 0.444 | |
2026.01 | 28.9 | 44.4 | |
2026.01 | 28.8 | 0.448 | |
2026.01 | 28.8 | 44.8 | |
2026.01 | 26.8 | 0.422 | |
2026.01 | 26.8 | 42.2 | |
2026.01 | 26.6 | 1.434 | |
2026.01 | 23.6 | 0.388 | |
2026.01 | 23.6 | 38.8 | |
2026.01 | 15.8 | 0.341 | |
2026.01 | 15.8 | 34.1 | |
2026.01 | 12.1 | 0.356 | |
2026.01 | 11.6 | 0.33 |