Fact Verification
73AccuracyFES-RAG-top5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FES-RAG-top5Model=Qwen2.5-VL2026.04 | 73 | 74.97 | |
| FES-RAG-top5Model=MM-RAIT-Qwen2.5VL2026.04 | 70 | 72.71 | |
| InfoGain-MM-top3Model=Qwen2.5-VL2026.04 | 70 | 73.75 | |
| InfoGain-MM-top3Model=MM-RAIT-Qwen2.5VL2026.04 | 68 | 69.8 | |
| FES-RAG-top5Model=InternVL3.52026.04 | 67 | 68.62 | |
| FES-RAG-top5Model=LLaVA-NeXT2026.04 | 65 | 65.69 | |
| Jina-Reranker-top3Model=MM-RAIT-Qwen2.5VL2026.04 | 63 | 64.31 | |
| Jina-Reranker-top3Model=Qwen2.5-VL2026.04 | 63 | 65.96 | |
| Naïve-MRAG-top3Model=MM-RAIT-Qwen2.5VL2026.04 | 62 | 62.95 | |
| Naïve-MRAG-top3Model=Qwen2.5-VL2026.04 | 60 | 62.26 | |
| None-MRAGModel=MM-RAIT-Qwen2.5VL2026.04 | 59 | 61.15 | |
| InfoGain-MM-top3Model=LLaVA-NeXT2026.04 | 55 | 38.25 | |
| InfoGain-MM-top3Model=InternVL3.52026.04 | 55 | 55.04 | |
| Jina-Reranker-top3Model=InternVL3.52026.04 | 52 | 52.02 | |
| None-MRAGModel=Qwen2.5-VL2026.04 | 51 | 50.67 | |
| Jina-Reranker-top3Model=LLaVA-NeXT2026.04 | 50 | 34.26 | |
| Naïve-MRAG-top3Model=LLaVA-NeXT2026.04 | 47 | 31.14 | |
| Naïve-MRAG-top3Model=InternVL3.52026.04 | 47 | 46.89 | |
| None-MRAGModel=InternVL3.52026.04 | 41 | 38.96 | |
| None-MRAGModel=LLaVA-NeXT2026.04 | 39 | 35.76 |