Hallucination Detection on CoQA (AUCs, AUCr, PCC)
77.5AUCs
LSC
Updated 3d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.01 | 77.5 | 75 | 41.2 | |
2026.01 | 75.3 | 73 | 30.1 | |
2026.01 | 74.6 | 71.2 | 30.1 | |
2026.01 | 73 | 71.9 | 34 | |
2026.01 | 72 | 71.8 | 38.4 | |
2026.01 | 71.6 | 71.8 | 34.6 | |
2026.01 | 71.5 | 71 | 38.7 | |
2026.01 | 71.5 | 70.9 | 34.7 | |
2026.01 | 71.4 | 73.4 | 40.5 | |
2026.01 | 71.3 | 72.6 | 36.3 | |
2026.01 | 71.2 | 70.7 | 41.1 | |
2026.01 | 69.5 | 73.9 | 37.8 | |
2026.01 | 69.4 | 69.2 | 27.9 | |
2026.01 | 69.3 | 69.3 | 31.4 | |
2026.01 | 69.1 | 69.1 | 27.4 | |
2026.01 | 68.7 | 72.9 | 36.1 | |
2026.01 | 68.4 | 68 | 35 | |
2026.01 | 68.2 | 71.7 | 29.9 | |
2026.01 | 67.7 | 72.1 | 31.3 | |
2026.01 | 67.2 | 69 | 31.7 | |
2026.01 | 67.2 | 67.9 | 29.1 | |
2026.01 | 67.2 | 66.7 | 25.7 | |
2026.01 | 67 | 66.1 | 25.7 | |
2026.01 | 66.6 | 68.3 | 19.9 | |
2026.01 | 66.4 | 69.1 | 32.8 | |
2026.01 | 65.7 | 66 | 25.5 | |
2026.01 | 65.1 | 65.7 | 19.6 | |
2026.01 | 62.2 | 63 | 20 | |
2026.01 | 60.2 | 61.9 | 11.8 | |
2026.01 | 58 | 63.8 | 16.5 | |
2026.01 | 56 | 58.6 | 9.7 | |
2026.01 | 55.3 | 62.1 | 8.4 | |
2026.01 | 55 | 58.5 | 8.3 | |
2026.01 | 51.6 | 59.1 | 4.7 | |
2026.01 | 48.9 | 54.9 | 4.2 | |
2026.01 | 47.9 | 56.8 | 0.1 | |
2026.01 | 44.3 | 52.3 | -7.1 | |
2026.01 | 43.7 | 50.5 | -9.7 | |
2026.01 | 43.1 | 47.2 | -8.2 | |
2026.01 | 41.1 | 44.2 | -10.1 | |
2026.01 | 36.8 | 39.8 | -17 | |
2026.01 | 26.5 | 36.7 | -20.3 |