Out-of-distribution Question Answering on CPIQA Clean
91.37AccuracyML Routing
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| ML RoutingEvaluation Context=non-refused test data, Domain=Out-of-distribution (OOD)2026.06 | 91.37 | 90.7 | — | |
| LWV FusionEvaluation Context=non-refused test data, Domain=Out-of-distribution (OOD)2026.06 | 82.11 | 79.1 | — | |
| FreeLBEvaluation Context=non-refused test data, Domain=Out-of-distribution (OOD)2026.06 | 48 | 55.97 | — | |
| Base ModelEvaluation Context=non-refused test data, Domain=Out-of-distribution (OOD)2026.06 | 45 | 43.86 | — |