Research map / Large language models / Agents, code and math
Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use CAAFE with GPT-4 rather than no feature engineering | TabPFN · Evaluated datasets | mean ROC AUC: 0.798 -> 0.822 | Helped |
| Use GPT-4 rather than GPT-3.5 for CAAFE feature generation | TabPFN · Evaluated datasets | mean ROC AUC: 0.806 -> 0.822 | Helped |
| Provide feature names and dataset description to CAAFE (ablation) | CAAFE (GPT-4) + TabPFN · Evaluated datasets | mean ROC AUC: 0.8 -> 0.822 | Helped |
| Provide feature names and dataset description to CAAFE (ablation) | CAAFE (GPT-4) + Logistic Regression · Evaluated datasets | mean ROC AUC: 0.749 -> 0.769 | Helped |
| Provide feature names and dataset description to CAAFE (ablation) | CAAFE (GPT-4) + Random Forest · Evaluated datasets | mean ROC AUC: 0.783 -> 0.803 | Helped |
Closest papers by meaning
- TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks (NeurIPS 2026 · similarity 0.88)
- Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning (ICML 2024 · similarity 0.86)
- A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data (NeurIPS 2024 · similarity 0.86)
- UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science (ICLR 2024 · similarity 0.86)
- Enhancing Tabular Learners with Context-Aware Semantic Embeddings (NeurIPS 2026 · similarity 0.86)
- TabFlex: Scaling Tabular Learning to Millions with Linear Attention (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.