RA-HMD (Qwen2-VL-2B)

Reported on 4 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Meme ClassificationonHateful Memes
Accuracy· 2025-02-18
0.791
best: 0.847 (Human)
Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection arXiv:2502.13061
Meme ClassificationonHateful Memes
ROC-AUC· 2025-02-18
0.884
best: 0.911 (RA-HMD (Qwen2-VL-7B))
Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection arXiv:2502.13061
Meme ClassificationonPrideMM
Accuracy· 2025-02-18
76
best: 78.1 (RA-HMD (Qwen2-VL-7B))
Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection arXiv:2502.13061
Meme ClassificationonPrideMM
F1· 2025-02-18
76.7
best: 78.4 (RA-HMD (Qwen2-VL-7B))
Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection arXiv:2502.13061