Multi-modal Stance Detection on MTWQ in-target
68.13MOC Macro F1MM-StanceDet
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MM-StanceDetModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 68.13 | 59.63 | |
| BridgeTowerModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 68.06 | 55.21 | |
| GPT-4 VisionModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 66.72 | 56.9 | |
| MV-DebateModality=Textual, Evaluation Protocol=in-target2026.04 | 58.71 | 50.49 | |
| GPT-4 + CoTModality=Textual, Evaluation Protocol=in-target2026.04 | 58.48 | 50.24 | |
| LKI-BARTModality=Textual, Evaluation Protocol=in-target2026.04 | 58.47 | 48.04 | |
| KEBERTModality=Textual, Evaluation Protocol=in-target2026.04 | 58.15 | 47.75 | |
| GPT-4Modality=Textual, Evaluation Protocol=in-target2026.04 | 58.05 | 49.81 | |
| BERTModality=Textual, Evaluation Protocol=in-target2026.04 | 57.77 | 45.91 | |
| TMPTModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 55.68 | 46.82 | |
| TASTEModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 55.48 | 54.91 | |
| LLaMA2Modality=Textual, Evaluation Protocol=in-target2026.04 | 55.31 | 46.51 | |
| CLIPModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 55.29 | 40.98 | |
| RoBERTaModality=Textual, Evaluation Protocol=in-target2026.04 | 55.22 | 48.88 | |
| BERT+ViTModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 47.47 | 40.86 | |
| ViLTModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 44.43 | 59.51 | |
| Qwen-VLModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 42.14 | 39.34 | |
| ResNetModality=Visual, Evaluation Protocol=in-target2026.04 | 42.02 | 33.94 | |
| ViTModality=Visual, Evaluation Protocol=in-target2026.04 | 38.63 | 35.53 | |
| SwinTModality=Visual, Evaluation Protocol=in-target2026.04 | 35.03 | 35.47 |