Relevance Classification on AliExpress (test)
68.36AccuracyMPCoT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MPCoTModel Category=Teacher Model, Protocol=SFT+DPO2026.01 | 68.36 | 65.9 | |
| Best-SingleCoTModel Category=Teacher Model, Protocol=SFT+DPO2026.01 | 64.83 | 58.26 | |
| MPCoTModel Category=Teacher Model, Protocol=SFT2026.01 | 64.45 | 62.18 | |
| ProgressiveCoTModel Category=Teacher Model, Protocol=SFT2026.01 | 61.47 | 54.22 | |
| Best-SingleCoTModel Category=Teacher Model, Protocol=SFT2026.01 | 59.81 | 53.87 | |
| LRKDModel Category=Student Model, Architecture=GAT2026.01 | 57.36 | 52.29 | |
| LRKDModel Category=Student Model, Architecture=Poly2026.01 | 56.92 | 51.37 | |
| CED-KDModel Category=Student Model2026.01 | 56.82 | 50.87 | |
| LRKDModel Category=Student Model, Architecture=MLP2026.01 | 56.04 | 50.98 | |
| MKDModel Category=Student Model2026.01 | 55.93 | 50.65 | |
| MPCoTModel Category=Teacher Model, Protocol=few-shot2026.01 | 55.86 | 48 | |
| Best-SingleCoTModel Category=Teacher Model, Protocol=few-shot2026.01 | 54.92 | 47.01 | |
| BERT-multilingual-baseModel Category=Deployable Model Baseline2026.01 | 53.17 | 49.34 |