Topic-oriented text understanding on Yahoo StandardCL (test)
70.34AccuracySynLearner
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SynLearnerBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 70.34 | 70.11 | |
| SynLearnerBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 69.25 | 68.94 | |
| DeepseekBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 69.24 | 69.05 | |
| DeepseekBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 68.83 | 68.39 | |
| GORPBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 68.25 | 68.42 | |
| LLaMA3.1-70BBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 68.24 | 68.32 | |
| GORPBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 67.83 | 67.92 | |
| FAPMBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 67.71 | 67.82 | |
| InsCLBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 67.53 | 67.7 | |
| SEEKRBackbone Model=Qwen2.5-7B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 67.26 | 67.35 | |
| LLaMA3.1-70BBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 67.17 | 67.19 | |
| LLaMA3.1-8BBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 66.88 | 66.93 | |
| SEEKRBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 66.59 | 66.54 | |
| FAPMBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 66.45 | 66.6 | |
| InsCLBackbone Model=LLaMA3.1-8B, Training Protocol=With Training (Continual Learning-Based Synthesis)2026.05 | 66.38 | 66.84 | |
| Qwen2.5-7BBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 66.2 | 65.79 | |
| OriBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 65.57 | 65.65 | |
| OriBackbone Model=Qwen2.5-7B, Training Protocol=No Training (Direct Synthesis)2026.05 | 65.03 | 65.09 | |
| LLaMA3.1-8BBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 64.87 | 65.37 | |
| Qwen2.5-7BBackbone Model=LLaMA3.1-8B, Training Protocol=No Training (Direct Synthesis)2026.05 | 64.16 | 64.05 |