Claim Verification on MR2
77.7Macro F1MEVER
Evaluation Results
| Method | Links | |
|---|---|---|
| MEVEREvidence Setting=Retrieved2026.02 | 77.7 | |
| MEVEREvidence Setting=Gold2026.02 | 76 | |
| CCNEvidence Setting=Retrieved2026.02 | 75.5 | |
| ESCNetEvidence Setting=Retrieved2026.02 | 75 | |
| ECENetEvidence Setting=Retrieved2026.02 | 74.2 | |
| MR2RetrievedEvidence Setting=Gold2026.02 | 73.9 | |
| CCNEvidence Setting=Gold2026.02 | 73.5 | |
| ESCNetEvidence Setting=Gold2026.02 | 73.5 | |
| TransformerXH++Evidence Setting=Retrieved2026.02 | 72.5 | |
| ECENetEvidence Setting=Gold2026.02 | 72.4 | |
| JustiLMEvidence Setting=Retrieved2026.02 | 72.1 | |
| MultiKE-GATEvidence Setting=Retrieved2026.02 | 71.6 | |
| MR2RetrievedEvidence Setting=Retrieved2026.02 | 71.2 | |
| TransformerXHEvidence Setting=Retrieved2026.02 | 70.9 | |
| CORRECTEvidence Setting=Retrieved2026.02 | 70.4 | |
| MEVER w/o imagesEvidence Setting=Retrieved2026.02 | 70.3 | |
| CORRECTEvidence Setting=Gold2026.02 | 70 | |
| JustiLMEvidence Setting=Gold2026.02 | 69.7 | |
| TransformerXH++Evidence Setting=Gold2026.02 | 69.6 | |
| GPT-4oEvidence Setting=Gold2026.02 | 68.7 | |
| TransformerXHEvidence Setting=Gold2026.02 | 68.1 | |
| MochegModelEvidence Setting=Retrieved2026.02 | 68 | |
| MEVER w/o imagesEvidence Setting=Gold2026.02 | 67.5 | |
| MultiKE-GATEvidence Setting=Gold2026.02 | 67 | |
| CausalWalkEvidence Setting=Retrieved2026.02 | 65.3 | |
| KGATEvidence Setting=Gold2026.02 | 65 | |
| RAVEvidence Setting=Gold2026.02 | 65 | |
| MochegModelEvidence Setting=Gold2026.02 | 64.8 | |
| CausalWalkEvidence Setting=Gold2026.02 | 64.6 | |
| KGATEvidence Setting=Retrieved2026.02 | 64.3 | |
| GPT-4oEvidence Setting=Retrieved2026.02 | 63.7 | |
| RAVEvidence Setting=Retrieved2026.02 | 61.9 |