Continual Learning on C-STANCE
46.8Average Accuracy (Acct)SETA
Evaluation results
| Method | Links | |
|---|---|---|
| SETABackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 46.8 | |
| I-LoRABackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 44.4 | |
| L2PBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 43.8 | |
| EWCBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 42.2 | |
| Seq-TrainBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 41.8 | |
| ERBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 40.8 | |
| A-GEMBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 40.2 | |
| GEMBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 38.8 | |
| PPBackbone=LLaMA-2 7B, Batch size=16, Learning rate=1e-42026.01 | 37.2 |