Classification on Messidor Feature UCIrvine (5-fold cross-validation)
0.7698Macro F1Dataforge
Evaluation results
| Method | Links | |
|---|---|---|
| DataforgeLLM Backbone=Llama-3.2-3B, Evaluation Protocol=5-fold cross-validation2025.11 | 0.7698 | |
| Pure LLMLLM Backbone=Llama 3.1, Evaluation Protocol=5-fold cross-validation2025.11 | 0.7561 | |
| ELLM-FTEvaluation Protocol=5-fold cross-validation2025.11 | 0.748 | |
| RL-Policy-2 (MOAT)Evaluation Protocol=5-fold cross-validation2025.11 | 0.7302 | |
| FeatLLMEvaluation Protocol=5-fold cross-validation2025.11 | 0.7262 | |
| RL-Policy-1 (GRFG)Evaluation Protocol=5-fold cross-validation2025.11 | 0.6924 | |
| OriginalEvaluation Protocol=5-fold cross-validation2025.11 | 0.6909 | |
| OpenFEEvaluation Protocol=5-fold cross-validation2025.11 | 0.6909 | |
| AutoFeatEvaluation Protocol=5-fold cross-validation2025.11 | 0.6908 | |
| PCAEvaluation Protocol=5-fold cross-validation2025.11 | 0.6721 | |
| ERGEvaluation Protocol=5-fold cross-validation2025.11 | 0.669 | |
| AFATEvaluation Protocol=5-fold cross-validation2025.11 | 0.6655 | |
| TTGEvaluation Protocol=5-fold cross-validation2025.11 | 0.6646 | |
| CAAFEEvaluation Protocol=5-fold cross-validation2025.11 | 0.661 | |
| NFSEvaluation Protocol=5-fold cross-validation2025.11 | 0.6377 | |
| RDGEvaluation Protocol=5-fold cross-validation2025.11 | 0.6238 | |
| LDAEvaluation Protocol=5-fold cross-validation2025.11 | 0.4752 |