Faithfulness Evaluation on Long-Form QA
0.795Correlation (Human Judgment)Fused Metric
Evaluation Results
| Method | Links | |
|---|---|---|
| Fused Metricmethodology=Explainable Boosting Machine2025.12 | 0.795 | |
| Prev. Best2025.12 | 0.659 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Fused Metricmethodology=Explainable Boosting Machine2025.12 | 0.795 | |
| Prev. Best2025.12 | 0.659 |