Review understanding on Yelp StandardCL (test)
66.11AccuracySynLearner
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SynLearnerBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 66.11 | 65.76 | |
| FAPMBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 65.89 | 65.33 | |
| InsCLBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 65.46 | 65.42 | |
| SEEKRBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 65.39 | 65.65 | |
| DeepseekBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 65.16 | 65.43 | |
| GORPBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 64.92 | 65.23 | |
| GORPBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 64.87 | 64.98 | |
| DeepseekBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 64.86 | 65.12 | |
| SynLearnerBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 63.91 | 64.13 | |
| FAPMBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 63.88 | 64.16 | |
| SEEKRBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 63.11 | 63.3 | |
| Qwen2.5-7BBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 62.08 | 62.17 | |
| Qwen2.5-7BBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 62.01 | 62.41 | |
| LLaMA3.1-70BBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 61.67 | 61.92 | |
| InsCLBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 61.53 | 60.29 | |
| LLaMA3.1-70BBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 60.74 | 61.06 | |
| LLaMA3.1-8BBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 59.87 | 60 | |
| LLaMA3.1-8BBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 58.66 | 59.04 | |
| OriBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 58.08 | 54.48 | |
| OriBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 55.42 | 54.77 |