Enriching Tabular Data with Contextual LLM Embeddings: A Comprehensive Ablation Study for Ensemble Classifiers
This work addresses feature engineering challenges for practitioners in tabular data classification, though it is incremental as it applies existing LLM methods to new data contexts.
This study tackled the problem of improving tabular data classification by enriching datasets with features from large language model embeddings, finding that integrating these embeddings with traditional features often enhanced predictive performance, especially for XGBoost and CatBoost on datasets like UCI Adult and Heart Disease.
Feature engineering is crucial for optimizing machine learning model performance, particularly in tabular data classification tasks. Leveraging advancements in natural language processing, this study presents a systematic approach to enrich tabular datasets with features derived from large language model embeddings. Through a comprehensive ablation study on diverse datasets, we assess the impact of RoBERTa and GPT-2 embeddings on ensemble classifiers, including Random Forest, XGBoost, and CatBoost. Results indicate that integrating embeddings with traditional numerical and categorical features often enhances predictive performance, especially on datasets with class imbalance or limited features and samples, such as UCI Adult, Heart Disease, Titanic, and Pima Indian Diabetes, with improvements particularly notable in XGBoost and CatBoost classifiers. Additionally, feature importance analysis reveals that LLM-derived features frequently rank among the most impactful for the predictions. This study provides a structured approach to embedding-based feature enrichment and illustrates its benefits in ensemble learning for tabular data.