MedHallu
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Hallucination Detection | MedHallu | AUROC1 | 24 | |
| Hallucination Detection | MedHallu (test) | Precision (HP)88.2 | 11 | |
| Generative Question Answering | MedHallu | HALL Score67.33 | 10 |
Showing 3 of 3 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Hallucination Detection | MedHallu | AUROC1 | 24 | |
| Hallucination Detection | MedHallu (test) | Precision (HP)88.2 | 11 | |
| Generative Question Answering | MedHallu | HALL Score67.33 | 10 |