Question Answering on SciQ (D_eval)
71.4AccuracyBelief-SR
Evaluation Results
| Method | Links | |
|---|---|---|
| Belief-SRModel=OLMo2025.02 | 71.4 | |
| VanillaModel=OLMo2025.02 | 68.9 | |
| Knowledge-SRModel=OLMo2025.02 | 65 | |
| Answer-SRModel=OLMo2025.02 | 62 | |
| Belief-SRModel=Pythia2025.02 | 60.2 | |
| VanillaModel=Pythia2025.02 | 57.3 | |
| Knowledge-SRModel=Pythia2025.02 | 57 | |
| Answer-SRModel=Pythia2025.02 | 55 | |
| Belief-SRModel=RPJ2025.02 | 52.6 | |
| VanillaModel=RPJ2025.02 | 48.6 | |
| Knowledge-SRModel=RPJ2025.02 | 47.8 | |
| Answer-SRModel=RPJ2025.02 | 44.2 |