HalluRAG
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Hallucination Detection | HalluRAG 1.0 (test) | F1 Score0.7274 | 30 | |
| Token-level hallucination detection | HalluRAG | AP76.9 | 18 | |
| Answer-level hallucination detection | HalluRAG | AP80.1 | 18 | |
| Span-level Hallucination Detection | HalluRAG (test) | F1 Score80.56 | 12 |
Showing 4 of 4 rows