SOURCE-LINKED INTELLIGENCE

LLMs as Feature Engineers for Text-and-Tabular Prediction

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

We introduce an iterative framework that automates the extraction of interpretable, schema-bound categorical features from unstructured text for tabular prediction models. To navigate the feature space, a generator LLM proposes semantic definitions, a separate extractor LLM materializes the features, and a downstream tabular model evaluates their predictive performance. We optimize this search by translating explicit model errors, such as AUC ranking inversions, into natural-language feedback, steering the LLM to resolve specific predictive failures. Evaluated across three public datasets, thi

Read original source ↗ Open in workspace

recordType

paper

region

Global