Question Answering on SciQ (train)
100AccuracyVanilla
Evaluation Results
| Method | Links | |
|---|---|---|
| VanillaModel=OLMo2025.02 | 100 | |
| VanillaModel=Pythia2025.02 | 100 | |
| VanillaModel=RPJ2025.02 | 100 | |
| Belief-SRModel=OLMo2025.02 | 95.4 | |
| Belief-SRModel=OLMo2025.02 | 95.2 | |
| VanillaModel=OLMo2025.02 | 94.5 | |
| Belief-SRModel=Pythia2025.02 | 93.4 | |
| Belief-SRModel=Pythia2025.02 | 93.2 | |
| Belief-SRModel=OLMo2025.02 | 92.8 | |
| Answer-SRModel=Pythia2025.02 | 92 | |
| VanillaModel=Pythia2025.02 | 91.8 | |
| Belief-SRModel=Pythia2025.02 | 91.7 | |
| Answer-SRModel=Pythia2025.02 | 91.7 | |
| Belief-SRModel=RPJ2025.02 | 91.4 | |
| Answer-SRModel=OLMo2025.02 | 91.1 | |
| Belief-SRModel=RPJ2025.02 | 91.1 | |
| Answer-SRModel=RPJ2025.02 | 91 | |
| Answer-SRModel=OLMo2025.02 | 91 | |
| Answer-SRModel=RPJ2025.02 | 90.7 | |
| Answer-SRModel=OLMo2025.02 | 90.6 | |
| Knowledge-SRModel=OLMo2025.02 | 90.2 | |
| Knowledge-SRModel=Pythia2025.02 | 90.1 | |
| Knowledge-SRModel=OLMo2025.02 | 90 | |
| Knowledge-SRModel=Pythia2025.02 | 89.7 | |
| VanillaModel=RPJ2025.02 | 89.6 | |
| Belief-SRModel=RPJ2025.02 | 89.3 | |
| Answer-SRModel=RPJ2025.02 | 89 | |
| Answer-SRModel=Pythia2025.02 | 88.5 | |
| Knowledge-SRModel=OLMo2025.02 | 87.1 | |
| Knowledge-SRModel=RPJ2025.02 | 87.1 | |
| Knowledge-SRModel=RPJ2025.02 | 86.4 | |
| Knowledge-SRModel=Pythia2025.02 | 85.4 | |
| Knowledge-SRModel=RPJ2025.02 | 80.5 | |
| VanillaModel=OLMo2025.02 | 0 | |
| VanillaModel=Pythia2025.02 | 0 | |
| VanillaModel=RPJ2025.02 | 0 |