Fact Verification on FEVER (EM)
61.1EMSAVER
Evaluation Results
| Method | Links | |
|---|---|---|
| SAVERBackbone=LLaMA-3.1-8B, Inference Setting=Zero-shot2026.04 | 61.1 | |
| SAVERBackbone=Qwen-2.5-7B, Inference Setting=Zero-shot2026.04 | 60.9 | |
| MADBackbone=LLaMA-3.1-8B, Inference Setting=Zero-shot2026.04 | 60.7 | |
| B-2Backbone=Qwen-2.5-7B, Inference Setting=Zero-shot2026.04 | 60.7 | |
| B-2Backbone=LLaMA-3.1-8B, Inference Setting=Zero-shot2026.04 | 60.6 | |
| MADBackbone=Qwen-2.5-7B, Inference Setting=Zero-shot2026.04 | 60.1 | |
| Self-RefineBackbone=Qwen-2.5-7B, Inference Setting=Zero-shot2026.04 | 58.2 | |
| Self-RefineBackbone=LLaMA-3.1-8B, Inference Setting=Zero-shot2026.04 | 57.6 | |
| SAVERBackbone=LLaMA-3.2-3B, Inference Setting=Zero-shot2026.04 | 56.4 | |
| CoTBackbone=Qwen-2.5-7B, Inference Setting=Zero-shot2026.04 | 56.3 | |
| CoTBackbone=LLaMA-3.1-8B, Inference Setting=Zero-shot2026.04 | 55.9 | |
| MADBackbone=LLaMA-3.2-3B, Inference Setting=Zero-shot2026.04 | 55.6 | |
| B-2Backbone=LLaMA-3.2-3B, Inference Setting=Zero-shot2026.04 | 54.3 | |
| Self-RefineBackbone=LLaMA-3.2-3B, Inference Setting=Zero-shot2026.04 | 53.8 | |
| Vanilla LMBackbone=LLaMA-3.1-8B, Inference Setting=Zero-shot2026.04 | 53.7 | |
| Vanilla LMBackbone=Qwen-2.5-7B, Inference Setting=Zero-shot2026.04 | 52.7 | |
| CoTBackbone=LLaMA-3.2-3B, Inference Setting=Zero-shot2026.04 | 52.4 | |
| Vanilla LMBackbone=LLaMA-3.2-3B, Inference Setting=Zero-shot2026.04 | 49.3 |