Classification on German Credit UCIrvine (5-fold cross-val)
0.796Macro F1Dataforge
Evaluation results
| Method | Links | |
|---|---|---|
| DataforgeLLM Backbone=Llama-3.2-3B, Evaluation Protocol=5-fold cross-validation2025.11 | 0.796 | |
| ELLM-FTEvaluation Protocol=5-fold cross-validation2025.11 | 0.7639 | |
| FeatLLMEvaluation Protocol=5-fold cross-validation2025.11 | 0.7635 | |
| Pure LLMLLM Backbone=Llama 3.1, Evaluation Protocol=5-fold cross-validation2025.11 | 0.7543 | |
| AutoFeatEvaluation Protocol=5-fold cross-validation2025.11 | 0.7486 | |
| OpenFEEvaluation Protocol=5-fold cross-validation2025.11 | 0.745 | |
| ERGEvaluation Protocol=5-fold cross-validation2025.11 | 0.7443 | |
| OriginalEvaluation Protocol=5-fold cross-validation2025.11 | 0.742 | |
| RL-Policy-2 (MOAT)Evaluation Protocol=5-fold cross-validation2025.11 | 0.7244 | |
| NFSEvaluation Protocol=5-fold cross-validation2025.11 | 0.6867 | |
| AFATEvaluation Protocol=5-fold cross-validation2025.11 | 0.6832 | |
| RL-Policy-1 (GRFG)Evaluation Protocol=5-fold cross-validation2025.11 | 0.6829 | |
| RDGEvaluation Protocol=5-fold cross-validation2025.11 | 0.6801 | |
| PCAEvaluation Protocol=5-fold cross-validation2025.11 | 0.6792 | |
| TTGEvaluation Protocol=5-fold cross-validation2025.11 | 0.6451 | |
| LDAEvaluation Protocol=5-fold cross-validation2025.11 | 0.6391 | |
| CAAFEEvaluation Protocol=5-fold cross-validation2025.11 | 0.5992 |