Review understanding on Amazon StandardCL (test)
60.22AccuracyDeepseek
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DeepseekBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 60.22 | 60.55 | |
| SynLearnerBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 60.09 | 60.39 | |
| GORPBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 58.74 | 59.12 | |
| SynLearnerBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 58.59 | 58.66 | |
| FAPMBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 58.42 | 58.64 | |
| InsCLBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 58.39 | 58.73 | |
| SEEKRBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 58.36 | 58.71 | |
| LLaMA3.1-70BBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 58.17 | 58.29 | |
| Qwen2.5-7BBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 57.86 | 58.03 | |
| FAPMBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 57.64 | 57.91 | |
| InsCLBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 57.54 | 57.8 | |
| LLaMA3.1-8BBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 57.46 | 57.76 | |
| DeepseekBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 57.29 | 57.49 | |
| SEEKRBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 57.18 | 57.39 | |
| GORPBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 56.82 | 57.09 | |
| LLaMA3.1-70BBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 56.61 | 56.88 | |
| Qwen2.5-7BBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 56.39 | 56.54 | |
| OriBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 55.41 | 55.47 | |
| OriBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 54.51 | 54.23 | |
| LLaMA3.1-8BBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 54.49 | 54.7 |