Semantic Hallucination Detection on PAWS
91.24AUROC
HALLUGUARD
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 91.24 | 88.53 | |
2026.01 | 90.18 | 87.64 | |
2026.01 | 86.38 | 83.41 | |
2026.01 | 85.63 | 82.14 | |
2026.01 | 85.47 | 82.38 | |
2026.01 | 85.41 | 82.27 | |
2026.01 | 84.56 | 81.37 | |
2026.01 | 84.26 | 81.73 | |
2026.01 | 83.92 | 81.06 | |
2026.01 | 83.59 | 79.42 | |
2026.01 | 82.71 | 78.89 | |
2026.01 | 80.46 | 77.28 | |
2026.01 | 80.42 | 77.18 | |
2026.01 | 79.47 | 76.28 | |
2026.01 | 79.06 | 76.32 | |
2026.01 | 78.93 | 75.41 | |
2026.01 | 78.53 | 75.21 | |
2026.01 | 78.29 | 75.44 | |
2026.01 | 77.82 | 73.41 | |
2026.01 | 77.43 | 73.29 | |
2026.01 | 77.39 | 74.18 | |
2026.01 | 77.14 | 74.28 | |
2026.01 | 76.72 | 72.63 | |
2026.01 | 76.23 | 72.59 | |
2026.01 | 75.68 | 71.42 | |
2026.01 | 75.11 | 72.41 | |
2026.01 | 73.56 | 70.43 | |
2026.01 | 73.46 | 68.32 | |
2026.01 | 73.05 | 70.22 | |
2026.01 | 72.62 | 67.58 | |
2026.01 | 72.19 | 68.34 | |
2026.01 | 71.27 | 67.55 | |
2026.01 | 69.54 | 64.27 | |
2026.01 | 68.44 | 63.58 | |
2026.01 | 68.35 | 63.44 | |
2026.01 | 64.58 | 59.67 |