Multi-modal Stance Detection on MRUC in-target
48.34RUS Macro F1MM-StanceDet
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MM-StanceDetModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 48.34 | 64.02 | |
| TASTEModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 45.89 | 46.12 | |
| CLIPModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 44.99 | 59.86 | |
| GPT-4 VisionModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 44.83 | 56.42 | |
| TMPTModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 43.56 | 59.24 | |
| BridgeTowerModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 43.26 | 58.19 | |
| GPT-4 + CoTModality=Textual, Evaluation Protocol=in-target2026.04 | 42.03 | 54.21 | |
| LKI-BARTModality=Textual, Evaluation Protocol=in-target2026.04 | 41.93 | 59.31 | |
| MV-DebateModality=Textual, Evaluation Protocol=in-target2026.04 | 41.89 | 54.55 | |
| GPT-4Modality=Textual, Evaluation Protocol=in-target2026.04 | 41.64 | 53.76 | |
| KEBERTModality=Textual, Evaluation Protocol=in-target2026.04 | 41.55 | 59.01 | |
| BERTModality=Textual, Evaluation Protocol=in-target2026.04 | 41.25 | 46.8 | |
| RoBERTaModality=Textual, Evaluation Protocol=in-target2026.04 | 39.52 | 57.66 | |
| BERT+ViTModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 39.28 | 48.41 | |
| LLaMA2Modality=Textual, Evaluation Protocol=in-target2026.04 | 38.84 | 38.54 | |
| Qwen-VLModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 36.5 | 40.78 | |
| ResNetModality=Visual, Evaluation Protocol=in-target2026.04 | 35.1 | 40 | |
| SwinTModality=Visual, Evaluation Protocol=in-target2026.04 | 35.01 | 40.89 | |
| ViLTModality=Multi-modal, Evaluation Protocol=in-target2026.04 | 34.62 | 42.41 | |
| ViTModality=Visual, Evaluation Protocol=in-target2026.04 | 33.31 | 39.87 |