Classification on Amazon Employee Kaggle (5-fold cross-validation)
94.41Macro F1Dataforge
Evaluation Results
| Method | Links | |
|---|---|---|
| DataforgeLLM Backbone=Llama-3.2-3B, Evaluation Protocol=5-fold cross-validation2025.11 | 94.41 | |
| FeatLLMEvaluation Protocol=5-fold cross-validation2025.11 | 93.62 | |
| OpenFEEvaluation Protocol=5-fold cross-validation2025.11 | 93.44 | |
| OriginalEvaluation Protocol=5-fold cross-validation2025.11 | 93.37 | |
| AutoFeatEvaluation Protocol=5-fold cross-validation2025.11 | 93.29 | |
| NFSEvaluation Protocol=5-fold cross-validation2025.11 | 93.21 | |
| ELLM-FTEvaluation Protocol=5-fold cross-validation2025.11 | 93.17 | |
| AFATEvaluation Protocol=5-fold cross-validation2025.11 | 92.97 | |
| TTGEvaluation Protocol=5-fold cross-validation2025.11 | 92.79 | |
| ERGEvaluation Protocol=5-fold cross-validation2025.11 | 92.43 | |
| RDGEvaluation Protocol=5-fold cross-validation2025.11 | 92.31 | |
| PCAEvaluation Protocol=5-fold cross-validation2025.11 | 92.29 | |
| LDAEvaluation Protocol=5-fold cross-validation2025.11 | 91.64 | |
| CAAFEEvaluation Protocol=5-fold cross-validation2025.11 | 91.41 | |
| Pure LLMLLM Backbone=Llama 3.1, Evaluation Protocol=5-fold cross-validation2025.11 | 75.43 | |
| RL-Policy-2 (MOAT)Evaluation Protocol=5-fold cross-validation2025.11 | 72.44 | |
| RL-Policy-1 (GRFG)Evaluation Protocol=5-fold cross-validation2025.11 | 68.29 |