Natural Language Understanding on GLUE (SST-2 Component)
90.4Accuracy (SST-2)FO
Evaluation results
| Method | Links | |
|---|---|---|
| FOBackbone=Qwen3-0.6b, Fine-tuning Protocol=First-order fine-tuning2026.01 | 90.4 | |
| AGZOBackbone=Qwen3-0.6b, Fine-tuning Protocol=Zeroth-order fine-tuning2026.01 | 87.7 | |
| LOZOBackbone=Qwen3-0.6b, Fine-tuning Protocol=Zeroth-order fine-tuning2026.01 | 87 | |
| MEZOBackbone=Qwen3-0.6b, Fine-tuning Protocol=Zeroth-order fine-tuning2026.01 | 85.8 | |
| ZeroBackbone=Qwen3-0.6b, Fine-tuning Protocol=Zero-shot prompting2026.01 | 54 | |
| ICLBackbone=Qwen3-0.6b, Fine-tuning Protocol=In-context learning2026.01 | 51 |