Fact-checking on CNN
62.1Balanced AccuracyANCHOR
Evaluation Results
| Method | Links | |
|---|---|---|
| ANCHORBackbone=Qwen2.5-72B, Direct Decision=false2026.05 | 62.1 | |
| VanillaBackbone=Qwen2.5-72B, Direct Decision=false2026.05 | 60.4 | |
| CoTBackbone=Qwen2.5-72B, Direct Decision=false2026.05 | 58.9 | |
| BIRDBackbone=Qwen2.5-72B, Direct Decision=false2026.05 | 54 | |
| VanillaBackbone=DeepSeek-V3-671B, Direct Decision=true2026.05 | 50 | |
| VanillaBackbone=Qwen2.5-72B, Direct Decision=true2026.05 | 50 | |
| CoTBackbone=Qwen2.5-72B, Direct Decision=true2026.05 | 50 | |
| VanillaBackbone=DeepSeek-V3-671B, Direct Decision=false2026.05 | 49.5 | |
| CoTBackbone=DeepSeek-V3-671B, Direct Decision=false2026.05 | 49.5 | |
| CoTBackbone=DeepSeek-V3-671B, Direct Decision=true2026.05 | 46.2 |