Claim Verification on AIChartClaim
71.6Macro F1MEVER
Evaluation Results
| Method | Links | |
|---|---|---|
| MEVEREvidence Setting=Gold2026.02 | 71.6 | |
| MEVEREvidence Setting=Retrieved2026.02 | 71.6 | |
| ECENetEvidence Setting=Retrieved2026.02 | 70.2 | |
| CORRECTEvidence Setting=Retrieved2026.02 | 70 | |
| ECENetEvidence Setting=Gold2026.02 | 70 | |
| MR2RetrievedEvidence Setting=Gold2026.02 | 69.9 | |
| MR2RetrievedEvidence Setting=Retrieved2026.02 | 69.8 | |
| CCNEvidence Setting=Gold2026.02 | 69.8 | |
| ESCNetEvidence Setting=Retrieved2026.02 | 69.6 | |
| ESCNetEvidence Setting=Gold2026.02 | 69.5 | |
| TransformerXH++Evidence Setting=Gold2026.02 | 69.4 | |
| CCNEvidence Setting=Retrieved2026.02 | 69.3 | |
| UniChartEvidence Setting=Gold2026.02 | 69.3 | |
| TransformerXHEvidence Setting=Retrieved2026.02 | 69.1 | |
| ChartGemmaEvidence Setting=Gold2026.02 | 69.1 | |
| CausalWalkEvidence Setting=Retrieved2026.02 | 69 | |
| KGATEvidence Setting=Retrieved2026.02 | 68.8 | |
| KGATEvidence Setting=Gold2026.02 | 68.7 | |
| TransformerXHEvidence Setting=Gold2026.02 | 68.6 | |
| ChartGemmaEvidence Setting=Retrieved2026.02 | 68.6 | |
| MEVER w/o imagesEvidence Setting=Retrieved2026.02 | 68.5 | |
| CausalWalkEvidence Setting=Gold2026.02 | 68.4 | |
| UniChartEvidence Setting=Retrieved2026.02 | 68.4 | |
| TransformerXH++Evidence Setting=Retrieved2026.02 | 68.3 | |
| CORRECTEvidence Setting=Gold2026.02 | 67.9 | |
| RAVEvidence Setting=Retrieved2026.02 | 67.6 | |
| RAVEvidence Setting=Gold2026.02 | 67.5 | |
| MultiKE-GATEvidence Setting=Retrieved2026.02 | 67.3 | |
| MultiKE-GATEvidence Setting=Gold2026.02 | 66.6 | |
| MEVER w/o imagesEvidence Setting=Gold2026.02 | 66.3 | |
| JustiLMEvidence Setting=Gold2026.02 | 65.4 | |
| JustiLMEvidence Setting=Retrieved2026.02 | 65.3 | |
| MochegModelEvidence Setting=Retrieved2026.02 | 59 | |
| MochegModelEvidence Setting=Gold2026.02 | 57.9 | |
| GPT-4oEvidence Setting=Gold2026.02 | 51 | |
| ChartBERTEvidence Setting=Retrieved2026.02 | 43 | |
| ChartBERTEvidence Setting=Gold2026.02 | 42.6 | |
| GPT-4oEvidence Setting=Retrieved2026.02 | 41.7 |