Out-of-distribution Question Answering on AERO Clean
92.5AccuracyLWV Fusion
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| LWV FusionEvaluation Context=non-refused test data, Domain=Out-of-distribution (OOD)2026.06 | 92.5 | 91.53 | — | |
| ML RoutingEvaluation Context=non-refused test data, Domain=Out-of-distribution (OOD)2026.06 | 92.5 | 89.5 | — | |
| FreeLBEvaluation Context=non-refused test data, Domain=Out-of-distribution (OOD)2026.06 | 62.52 | 61.84 | — | |
| Base ModelEvaluation Context=non-refused test data, Domain=Out-of-distribution (OOD)2026.06 | 49 | 47.34 | — |