LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers
This addresses the challenge of improving predictive model performance for tabular learning tasks by integrating domain knowledge and data-driven feedback, though it appears incremental as it builds on existing LLM-based methods.
The paper tackled the problem of automated feature engineering for tabular data by proposing LLM-FE, a framework that combines evolutionary search with LLMs to discover effective features, resulting in consistent outperformance of state-of-the-art baselines across diverse benchmarks.
Automated feature engineering plays a critical role in improving predictive model performance for tabular learning tasks. Traditional automated feature engineering methods are limited by their reliance on pre-defined transformations within fixed, manually designed search spaces, often neglecting domain knowledge. Recent advances using Large Language Models (LLMs) have enabled the integration of domain knowledge into the feature engineering process. However, existing LLM-based approaches use direct prompting or rely solely on validation scores for feature selection, failing to leverage insights from prior feature discovery experiments or establish meaningful reasoning between feature generation and data-driven performance. To address these challenges, we propose LLM-FE, a novel framework that combines evolutionary search with the domain knowledge and reasoning capabilities of LLMs to automatically discover effective features for tabular learning tasks. LLM-FE formulates feature engineering as a program search problem, where LLMs propose new feature transformation programs iteratively, and data-driven feedback guides the search process. Our results demonstrate that LLM-FE consistently outperforms state-of-the-art baselines, significantly enhancing the performance of tabular prediction models across diverse classification and regression benchmarks.