Question Answering on OpenBookQA D^x (train)
93.5AccuracyBelief-SR
Evaluation results
| Method | Links | |
|---|---|---|
| Belief-SRModel=OLMo2025.02 | 93.5 | |
| Belief-SRModel=RPJ2025.02 | 93.3 | |
| Belief-SRModel=Pythia2025.02 | 90.4 | |
| Answer-SRModel=OLMo2025.02 | 88.3 | |
| Knowledge-SRModel=OLMo2025.02 | 87.9 | |
| Answer-SRModel=RPJ2025.02 | 85.8 | |
| Knowledge-SRModel=Pythia2025.02 | 83.3 | |
| Answer-SRModel=Pythia2025.02 | 83.1 | |
| Knowledge-SRModel=RPJ2025.02 | 80.1 | |
| VanillaModel=OLMo2025.02 | 0 | |
| VanillaModel=Pythia2025.02 | 0 | |
| VanillaModel=RPJ2025.02 | 0 |