Hateful Meme Classification On Harm P
Metrics
Accuracy
F1
Results
Performance results of various models on this benchmark
Model Name | Accuracy | F1 | Paper Title | Repository |
|---|---|---|---|---|
| hateclipper | 87.6 | 86.9 | Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features | |
| RGCL | 89.9 | 89.5 | Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning | |
| LMM-RGCL (Qwen2-VL-7B) | 91.6 | 91.1 | Improved Fine-Tuning of Large Multimodal Models for Hateful Meme Detection | |
| ExplainHM | 90.7 | 90.7 | Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models | |
| CLIP | 80.6 | 80.3 | Learning Transferable Visual Models From Natural Language Supervision |
0 of 5 row(s) selected.