Uncertainty Estimation on NewsQA
76.6AUROC
Self-Consistency
Updated 26d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 76.6 | 80.7 | 70.2 | 161.1 | |
2026.05 | 76.1 | 79.8 | 71.4 | 161.1 | |
2026.05 | 75.9 | 84.6 | 69.7 | 8.9 | |
2026.05 | 75.7 | 63.3 | 68.3 | 27.2 | |
2026.05 | 75.5 | 83.3 | 69.2 | 9.7 | |
2026.05 | 75.3 | 77.2 | 68.6 | 24.1 | |
2026.05 | 75.1 | 79.4 | 70.5 | 15.7 | |
2026.05 | 75 | 79.4 | 69.9 | 11.7 | |
2026.05 | 74.9 | 74.4 | 68.9 | 24.1 | |
2026.05 | 74.2 | 77.9 | 69.6 | 15.7 | |
2026.05 | 73.9 | 63.4 | 68.7 | 23.1 | |
2026.05 | 72.8 | 53.2 | 66.6 | 29 | |
2026.05 | 72.7 | 53 | 67.3 | 29 | |
2026.05 | 72.7 | 75.1 | 66.7 | 16.3 | |
2026.05 | 72.2 | 77.4 | 67.1 | 16.3 | |
2026.05 | 71.9 | 81.7 | 65.7 | 9.7 | |
2026.05 | 71.7 | 78.8 | 65.6 | 0 | |
2026.05 | 71.7 | 83.6 | 65.9 | 0 | |
2026.05 | 71.4 | 82.2 | 64.8 | 0 | |
2026.05 | 71.1 | 65 | 64 | 20.8 | |
2026.05 | 70.4 | 65.6 | 65.5 | 20.8 | |
2026.05 | 69.9 | 65.2 | 64.8 | 16 | |
2026.05 | 69.6 | 65.6 | 64.3 | 20.8 | |
2026.05 | 69.4 | 82.3 | 64.7 | 8.9 | |
2026.05 | 68.6 | 76.3 | 63.7 | 0 | |
2026.05 | 67.9 | 74.2 | 63 | 0 | |
2026.05 | 66.3 | 81.3 | 60.8 | 8.9 | |
2026.05 | 65.1 | 74.5 | 59.8 | 15.7 | |
2026.05 | 64.8 | 75.6 | 60.5 | 15.7 | |
2026.05 | 63.4 | 56.2 | 59 | 27.2 | |
2026.05 | 63.2 | 78.2 | 59.2 | 9.7 | |
2026.05 | 61.7 | 59.9 | 57.9 | 0 | |
2026.05 | 61.2 | 58.3 | 58.5 | 209.7 | |
2026.05 | 61.2 | 58.5 | 57.7 | 209.7 | |
2026.05 | 60.3 | 45.2 | 57.2 | 29 | |
2026.05 | 58.2 | 52.9 | 55.7 | 0 | |
2026.05 | 57.7 | 43.8 | 55.1 | 0 | |
2026.05 | 56.6 | 71.3 | 54.8 | 15.7 | |
2026.05 | 55.3 | 69.2 | 53.4 | 16.3 | |
2026.05 | 54.8 | 66.9 | 53.4 | 24.1 | |
2026.05 | 51.1 | 54.2 | 53.5 | 20.8 | |
2026.05 | 46.2 | 50.5 | 51.1 | 20.8 |