Content Moderation
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Content Moderation | Content Moderation Korean (test) | Abusive Rate64.7 | 4 | |
| Content Moderation | Content Moderation Chinese (test) | Bias23.7 | 3 | |
| Content Moderation | Content Moderation Arabic (test) | Hate Accuracy55.8 | 2 |
Showing 3 of 3 rows