Concept Detection on European Parliament Language (test)
94.3AccuracyEnsembling (NB)
Evaluation results
| Method | Links | |
|---|---|---|
| Ensembling (NB)Base Model=Pythia-70M, Ensemble Size=8, Number of top concept-associated features=12025.05 | 94.3 | |
| Expanded SAEBase Model=Pythia-70M, Ensemble Size=1, Number of top concept-associated features=12025.05 | 94.2 | |
| Ensembling (Boosting)Base Model=Pythia-70M, Ensemble Size=8, Number of top concept-associated features=12025.05 | 92 |