BABE
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| STEM Knowledge | BABE | Score58.1 | 9 | |
| Bias Detection | BABE (test) | Macro F180.8 | 8 | |
| Sentence-level binary bias detection | BABE (test) | F1 Score85.3 | 7 | |
| Fine-grained bias type classification | BABE type-annotated | Macro-F161.4 | 4 |
Showing 4 of 4 rows