Counterfactual
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Knowledge cutoff success | Counterfactual | Hard Unlearn Success Rate71.2 | 21 | |
| Compositional Out-of-Distribution Detection | Counterfactual dataset | AUC0.942 | 17 | |
| Counterfactual error detection | Counterfactual dataset | Finding Detection Rate24 | 5 | |
| Stereotyping Evaluation | Counterfactual Open-Ended (OCF) | Stereotype Fraction2.5 | 5 |
Showing 4 of 4 rows