Uncertainty Estimation on TruthfulQA
26.8PRR
Internal Confidence
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.06 | 26.8 | 63.2 | 15.4 | |
2025.06 | 22.8 | 58.1 | - | |
2025.06 | 21.1 | 59.9 | - | |
2025.06 | 21 | 57.8 | - | |
2025.06 | 16.4 | 58 | 0.5 | |
2025.06 | 15.6 | 55.7 | - | |
2025.06 | 13.9 | 55.1 | - | |
2025.06 | 13.7 | 60 | - | |
2025.06 | 13.2 | 56.4 | 40.7 | |
2025.06 | 9.6 | 53.3 | - | |
2025.06 | 8.3 | 52.4 | - | |
2025.06 | 6 | 52.6 | - | |
2025.06 | 4.8 | 54.3 | - | |
2025.06 | 4.7 | 51 | - | |
2025.06 | 4.1 | 52.4 | - | |
2025.06 | 3.8 | 54.1 | - | |
2025.06 | 3.2 | 50.7 | - | |
2025.06 | 1.9 | 47 | 3.4 | |
2026.06 | 0.392 | - | - | |
2026.06 | 0.377 | - | - | |
2026.06 | 0.347 | - | - | |
2026.06 | 0.31 | - | - | |
2026.06 | 0.307 | - | - | |
2026.06 | 0.282 | - | - | |
2026.06 | 0.267 | - | - | |
2026.06 | 0.195 | - | - | |
2026.06 | 0.192 | - | - | |
2026.06 | 0.185 | - | - | |
2026.06 | 0.181 | - | - | |
2026.06 | 0.154 | - | - | |
2026.06 | 0.115 | - | - | |
2026.06 | 0.102 | - | - | |
2026.06 | 0.091 | - | - | |
2026.06 | 0.087 | - | - | |
2026.06 | 0.063 | - | - | |
2026.06 | -0.094 | - | - | |
2025.06 | -1.3 | 50.3 | - | |
2025.06 | -2 | 49.3 | 25.5 | |
2025.06 | -3.5 | 49.7 | 8.6 | |
2025.06 | -11.9 | 43.3 | 55.7 | |
2025.06 | -16.2 | 39.6 | 27.1 | |
2025.06 | -19 | 42.6 | 53.4 | |
2026.04 | - | 57.9 | - | |
2026.04 | - | 52.8 | - | |
2026.04 | - | 63.9 | - | |
2026.04 | - | 60.3 | - | |
2026.04 | - | 60.2 | - | |
2026.04 | - | 51.4 | - | |
2026.04 | - | 58.1 | - | |
2026.04 | - | 53.4 | - | |
2026.04 | - | 54.4 | - | |
2026.04 | - | 54.2 | - | |
2026.04 | - | 52.7 | - | |
2026.04 | - | 52.8 | - | |
2026.04 | - | 58.6 | - | |
2026.04 | - | 45.1 | - | |
2026.04 | - | 53.4 | - | |
2026.04 | - | 63.7 | - |