Multiple-choice Question Answering on MMLU-ProX (T1)
23.5AccuracyEWC
Evaluation results
| Method | Links | |
|---|---|---|
| EWCBackbone=LLaMA-3.1-Instruct-8B, Number of random seeds=32026.04 | 23.5 | |
| Full RetrainingBackbone=LLaMA-3.1-Instruct-8B, Number of random seeds=32026.04 | 23.4 | |
| Naive Fine-tuningBackbone=LLaMA-3.1-Instruct-8B, Number of random seeds=32026.04 | 23.3 | |
| COMPASS-ECDABackbone=LLaMA-3.1-Instruct-8B, Number of random seeds=32026.04 | 23.2 | |
| Random RehearsalBackbone=LLaMA-3.1-Instruct-8B, Number of random seeds=32026.04 | 23 |