Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Hate Speech Detection On Hatexplain

Metrics

AUROC

Accuracy

Macro F1

Results

Performance results of various models on this benchmark

Model Name	AUROC	Accuracy	Macro F1	Paper Title	Repository
CNN-GRU [LIME]	0.793	0.629	0.614	HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection
BERT [Attn]	0.843	0.69	0.674	HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection
BiRNN-HateXplain [Attn]	0.805	-	0.629	HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection
XG-HSI-BiRNN	-	0.742	-	Explainable Identification of Hate Speech towards Islam using Graph Neural Networks	-
XG-HSI-BERT	-	0.751	-	Explainable Identification of Hate Speech towards Islam using Graph Neural Networks	-
BiRNN-Attn [Attn]	0.795	0.621	-	HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection
BERT-HateXplain [Attn]	0.851	0.698	0.687	HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection
BERT-HateXplain [LIME]	0.851	-	0.687	HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection
BiRNN [LIME]	0.767	0.595	0.575	HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection
BERT-RP	0.853	0.707	0.693	Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detection	-
BERT-MRP	0.862	0.704	0.699	Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detection	-

0 of 11 row(s) selected.