Uncertainty Estimation on TriviaQA
88AUROC
Geometry-Calibrated Conformal Abstention
Updated 1mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| 88 | - | - | - | 87 | ||
2026.04 | 85.56 | - | 17.78 | - | - | |
2026.04 | 85.56 | - | 20.38 | 2.6 | - | |
2026.04 | 84.6 | - | 37.83 | - | - | |
2026.04 | 84.6 | - | 18.88 | -18.95 | - | |
2024.02 | 83.63 | - | - | - | - | |
2023.08 | 82.8 | - | - | - | - | |
2024.02 | 82.22 | - | - | - | - | |
2024.02 | 82.17 | - | - | - | - | |
2023.08 | 81.7 | - | - | - | - | |
2026.04 | 81.5 | - | - | - | - | |
2024.02 | 81.1 | - | - | - | - | |
2024.02 | 81 | - | - | - | - | |
2026.04 | 80 | - | - | - | 67 | |
2026.04 | 79.6 | - | - | - | - | |
2024.02 | 79.49 | - | - | - | - | |
2026.04 | 79.12 | - | 5.39 | -11.68 | - | |
2026.04 | 78.92 | - | 17.07 | - | - | |
2024.02 | 78.51 | - | - | - | - | |
2026.04 | 78.05 | - | 12.15 | -15.56 | - | |
2024.02 | 77.97 | - | - | - | - | |
2024.02 | 77.67 | - | - | - | - | |
2024.02 | 77.48 | - | - | - | - | |
2026.04 | 76.91 | - | 20.53 | - | - | |
2026.04 | 76.91 | - | 11.66 | -8.87 | - | |
2023.08 | 76.9 | - | - | - | - | |
2024.02 | 76.78 | - | - | - | - | |
2026.04 | 76.76 | - | 4.75 | -4.88 | - | |
2026.04 | 76.42 | - | 9.63 | - | - | |
2024.02 | 76.19 | - | - | - | - | |
2026.04 | 76.15 | - | 48.25 | - | - | |
2026.04 | 76.15 | - | 13.41 | -34.84 | - | |
2024.02 | 75.94 | - | - | - | - | |
2026.04 | 75.79 | - | 30.31 | - | - | |
2026.04 | 75.79 | - | 8.53 | -21.78 | - | |
2026.04 | 75.3 | - | 4.07 | -18.64 | - | |
2024.02 | 75.06 | - | - | - | - | |
2024.02 | 74.95 | - | - | - | - | |
2026.04 | 74.43 | - | 22.71 | - | - | |
2024.02 | 74.23 | - | - | - | - | |
2024.02 | 73.99 | - | - | - | - | |
2026.04 | 73.87 | - | 29.34 | - | - | |
2026.04 | 73.87 | - | 7.96 | -21.37 | - | |
2024.02 | 73.82 | - | - | - | - | |
2026.04 | 73.38 | - | 7.63 | -13.27 | - | |
2026.04 | 73.1 | - | - | - | - | |
2024.02 | 72.95 | - | - | - | - | |
2024.02 | 72.87 | - | - | - | - | |
2024.02 | 72.57 | - | - | - | - | |
2024.02 | 72.55 | - | - | - | - | |
2026.04 | 72.3 | - | - | - | - | |
2023.08 | 70.8 | - | - | - | - | |
2026.04 | 70.6 | - | - | - | - | |
2026.04 | 70.53 | - | 10.21 | - | - | |
2026.04 | 70.53 | - | 8.52 | -1.69 | - | |
2024.02 | 70.4 | - | - | - | - | |
2026.04 | 70.2 | - | - | - | - | |
2024.02 | 70.18 | - | - | - | - | |
2026.04 | 70 | - | - | - | 52 | |
2024.02 | 69.94 | - | - | - | - | |
2024.02 | 69.7 | - | - | - | - | |
2026.04 | 69.6 | - | - | - | - | |
2026.04 | 69.19 | - | 58.46 | - | - | |
2024.02 | 69.1 | - | - | - | - | |
2024.02 | 69.04 | - | - | - | - | |
2026.04 | 69 | - | - | - | - | |
2023.08 | 68.9 | - | - | - | - | |
2026.04 | 68.68 | - | 3.85 | -36.54 | - | |
2024.02 | 68.47 | - | - | - | - | |
2026.04 | 68.37 | - | 27.7 | - | - | |
2024.02 | 68.19 | - | - | - | - | |
2026.04 | 67.4 | - | - | - | - | |
2026.04 | 67.3 | - | - | - | - | |
2026.04 | 67.2 | - | - | - | - | |
2026.04 | 67.11 | - | 6.51 | -51.95 | - | |
2026.04 | 67 | - | - | - | 60 | |
2026.04 | 66.7 | - | - | - | - | |
2026.04 | 66 | - | - | - | - | |
2026.04 | 66 | - | - | - | 51 | |
2026.04 | 66 | - | - | - | 52 | |
2026.04 | 65.69 | - | 6.58 | -52.86 | - | |
2023.08 | 65.5 | - | - | - | - | |
2023.08 | 65.3 | - | - | - | - | |
2026.04 | 65.19 | - | 3.92 | -12.48 | - | |
2026.04 | 65 | - | - | - | 55 | |
2026.04 | 64 | - | - | - | 51 | |
2026.04 | 63.7 | - | - | - | - | |
2026.04 | 63.62 | - | 2.16 | -36.82 | - | |
2026.04 | 63.08 | - | 8.89 | -37.59 | - | |
2026.04 | 63 | - | - | - | - | |
2026.04 | 62.87 | - | 38.98 | - | - | |
2026.04 | 62.43 | - | 46.47 | - | - | |
2026.04 | 62.21 | - | 4.12 | -34.44 | - | |
2026.04 | 62.16 | - | 38.56 | - | - | |
2026.04 | 59.18 | - | 20.9 | - | - | |
2026.04 | 58 | - | - | - | 41 | |
2026.04 | 54.6 | - | 16.4 | - | - | |
2026.04 | 53 | - | - | - | 40 | |
2026.04 | 52.08 | - | 59.45 | - | - | |
2026.04 | 52 | - | - | - | 39 |
Showing 100 of 139 rows