Question Answering on HotpotQA D^x (train)
92.6AccuracyAnswer-SR
Evaluation Results
| Method | Links | |
|---|---|---|
| Answer-SRModel=OLMo2025.02 | 92.6 | |
| Belief-SRModel=RPJ2025.02 | 88 | |
| Answer-SRModel=RPJ2025.02 | 87.7 | |
| Belief-SRModel=Pythia2025.02 | 87.7 | |
| Knowledge-SRModel=RPJ2025.02 | 86.9 | |
| Belief-SRModel=OLMo2025.02 | 86.6 | |
| Answer-SRModel=Pythia2025.02 | 86.1 | |
| Knowledge-SRModel=Pythia2025.02 | 83.7 | |
| Knowledge-SRModel=OLMo2025.02 | 81 | |
| VanillaModel=OLMo2025.02 | 0 | |
| VanillaModel=Pythia2025.02 | 0 | |
| VanillaModel=RPJ2025.02 | 0 |