e-Commerce Task on Internal e-commerce benchmark Task medium-scale seller 387 items
54.3Performance ScoreBaseline
Evaluation Results
| Method | Links | |
|---|---|---|
| BaselineBase Model=Llama 3.1 8B2025.05 | 54.3 | |
| ME+GDBase Model=Llama 3.1 8B2025.05 | 54.3 | |
| UnDIAL+KLBase Model=Llama 3.1 8B, Variant=12025.05 | 54.2 | |
| UnDIAL+KLBase Model=Llama 3.1 8B, Variant=22025.05 | 54.1 | |
| RKLD+KLBase Model=Llama 3.1 8B2025.05 | 53.8 | |
| Unilogit+KLBase Model=Llama 3.1 8B, Variant=22025.05 | 53.8 | |
| NPO+KLBase Model=Llama 3.1 8B, Variant=22025.05 | 53.7 | |
| SimNPO+KLBase Model=Llama 3.1 8B, Variant=22025.05 | 53.5 | |
| GA+KLBase Model=Llama 3.1 8B2025.05 | 53.4 | |
| GABase Model=Llama 3.1 8B2025.05 | 53.1 | |
| NPO+KLBase Model=Llama 3.1 8B, Variant=12025.05 | 53 | |
| SimNPO+KLBase Model=Llama 3.1 8B, Variant=12025.05 | 52.6 | |
| NPOBase Model=Llama 3.1 8B2025.05 | 51.8 | |
| Unilogit+KLBase Model=Llama 3.1 8B, Variant=12025.05 | 43.4 |