Metric: Macro F1 (higher is better)
| # | Model↕ | Macro F1▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | BERT-MRP | 0.699 | No | Why Is It Hate Speech? Masked Rationale Predicti... | 2022-11-01 | Code |
| 2 | BERT-RP | 0.693 | No | Why Is It Hate Speech? Masked Rationale Predicti... | 2022-11-01 | Code |
| 3 | BERT-HateXplain [Attn] | 0.687 | No | HateXplain: A Benchmark Dataset for Explainable ... | 2020-12-18 | Code |
| 4 | BERT-HateXplain [LIME] | 0.687 | No | HateXplain: A Benchmark Dataset for Explainable ... | 2020-12-18 | Code |
| 5 | BERT [Attn] | 0.674 | No | HateXplain: A Benchmark Dataset for Explainable ... | 2020-12-18 | Code |
| 6 | BiRNN-HateXplain [Attn] | 0.629 | No | HateXplain: A Benchmark Dataset for Explainable ... | 2020-12-18 | Code |
| 7 | CNN-GRU [LIME] | 0.614 | No | HateXplain: A Benchmark Dataset for Explainable ... | 2020-12-18 | Code |
| 8 | BiRNN [LIME] | 0.575 | No | HateXplain: A Benchmark Dataset for Explainable ... | 2020-12-18 | Code |