UMWP
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Hallucination Detection | UMWP | ROC-AUC89.6 | 28 | |
| Hallucination Detection (Math Word Problems) | UMWP | F1 Score89.1 | 12 | |
| Math Reasoning | UMWP | False Positive Rate0.62 | 5 |
Showing 3 of 3 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Hallucination Detection | UMWP | ROC-AUC89.6 | 28 | |
| Hallucination Detection (Math Word Problems) | UMWP | F1 Score89.1 | 12 | |
| Math Reasoning | UMWP | False Positive Rate0.62 | 5 |