Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Hate Speech

Benchmarks

Task NameDataset NameSOTA ResultTrend
Hate Speech DetectionHate Speech
Accuracy90.51
49
Toxicity DetectionHate Speech
Accuracy75.73
10
Multimodal GenerationHate Speech
BLEU-L31.04
6
DetectionHate speech18
Macro F10.573
6
Text ClassificationHate Speech Plain-text OOD (test)
Accuracy22.2
4
Binary classificationhate-speech English (test)
Accuracy92
3
DetectionHate speech18 (test)
Macro F144.3
3
Showing 7 of 7 rows