| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Hallucination Detection | PsiloQA | AUROC92.64 | 56 | |
| Hallucination Detection | PsiloQA | Accuracy88.43 | 14 | |
| Span-level Hallucination Detection | PsiloQA (test) | F1 Score73.2 | 3 | |
| Hallucination Detection | PsiloQA 14-lang IoU | IoU68.9 | 3 | |
| Hallucination Detection | PsiloQA EN (IoU) | IoU72.4 | 3 |