Language Understanding on MMLU-ProX
27.7AccuracyNaive Fine-tuning
Evaluation Results
| Method | Links | |
|---|---|---|
| Naive Fine-tuningBackbone=Phi-4-Mini-Instruct-3.8B2026.04 | 27.7 | |
| COMPASS-ECDABackbone=Phi-4-Mini-Instruct-3.8B2026.04 | 27.6 | |
| Full RetrainingBackbone=Phi-4-Mini-Instruct-3.8B2026.04 | 27.5 | |
| EWCBackbone=Phi-4-Mini-Instruct-3.8B2026.04 | 27.2 | |
| Random RehearsalBackbone=Phi-4-Mini-Instruct-3.8B2026.04 | 27 |