Automatic Text Evaluation on Amazon (MAE, MSE)
0.209MAECoR
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CoRBase Model=DeepSeek2025.12 | 0.209 | 0.234 | |
| QWQ-32BBase Model=Qwen-2.5, Parameter Size=32B2025.12 | 0.215 | 0.327 | |
| DeepSEEK-R1Base Model=DeepSeek2025.12 | 0.222 | 0.246 | |
| M-2Type=Task-Specific Baseline2025.12 | 0.226 | 0.235 | |
| CoTBase Model=DeepSeek2025.12 | 0.312 | 0.387 | |
| RuAE-7BBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 0.366 | 0.519 | |
| CoTBase Model=Qwen-2.5, Parameter Size=32B2025.12 | 1.119 | 2.004 | |
| CoRBase Model=Qwen-2.5, Parameter Size=32B2025.12 | 1.123 | 2.017 | |
| CoTBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 1.18 | 2.21 | |
| ScoringBase Model=DeepSeek2025.12 | 1.182 | 2.184 | |
| CoRBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 1.2 | 2.3 | |
| ScoringBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 1.21 | 2.28 | |
| ScoringBase Model=Qwen-2.5, Parameter Size=32B2025.12 | 1.212 | 2.235 | |
| M-1Type=Task-Specific Baseline2025.12 | 1.22 | 2.41 | |
| SFT-7BBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 1.93 | 5.54 |