Uncertainty Estimation on Natural Questions (NQ)
0.77AUROCProposed
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ProposedBackbone Model=LLaMA-3-8B-Instruct2026.04 | 0.77 | 0.81 | |
| SARBackbone Model=LLaMA-3-8B-Instruct2026.04 | 0.75 | 0.8 | |
| PerplexityBackbone Model=LLaMA-3-8B-Instruct2026.04 | 0.67 | 0.73 | |
| FocusBackbone Model=LLaMA-3-8B-Instruct2026.04 | 0.64 | 0.69 | |
| SemanticBackbone Model=LLaMA-3-8B-Instruct2026.04 | 0.63 | 0.68 | |
| P(True)Backbone Model=LLaMA-3-8B-Instruct2026.04 | 0.61 | 0.65 | |
| EigenBackbone Model=LLaMA-3-8B-Instruct2026.04 | 0.57 | 0.64 | |
| ATRMDBackbone Model=LLaMA-3-8B-Instruct2026.04 | 0.54 | 0.62 | |
| AttentionBackbone Model=LLaMA-3-8B-Instruct2026.04 | 0.49 | 0.57 |