Classification on Diabetes (val)
85.2AUROC (%)Human-LLM Collaborative Feature Engineering Framework
Evaluation Results
| Method | Links | |
|---|---|---|
| Human-LLM Collaborative Feature Engineering FrameworkDownstream Model=XGBoost, LLM Backbone=GPT-4o, Human Involvement=Absent2026.01 | 85.2 | |
| Human-LLM Collaborative Feature Engineering FrameworkDownstream Model=XGBoost, LLM Backbone=GPT-4o, Human Involvement=Active2026.01 | 84.8 | |
| OCTreeDownstream Model=XGBoost, LLM Backbone=GPT-4o2026.01 | 84.4 | |
| OpenFEDownstream Model=XGBoost2026.01 | 84.1 | |
| AutoGluonDownstream Model=XGBoost2026.01 | 83.9 | |
| CAAFEDownstream Model=XGBoost, LLM Backbone=GPT-4o2026.01 | 83.9 | |
| Human-LLM Collaborative Feature Engineering FrameworkDownstream Model=MLP, LLM Backbone=GPT-4o, Human Involvement=Absent2026.01 | 83 | |
| Human-LLM Collaborative Feature Engineering FrameworkDownstream Model=MLP, LLM Backbone=GPT-4o, Human Involvement=Active2026.01 | 83 | |
| CAAFEDownstream Model=MLP, LLM Backbone=GPT-4o2026.01 | 82.8 | |
| OCTreeDownstream Model=MLP, LLM Backbone=GPT-4o2026.01 | 82.8 | |
| AutoGluonDownstream Model=MLP2026.01 | 82.4 | |
| OpenFEDownstream Model=MLP2026.01 | 81.1 |