# LLMs as Feature Engineers for Text-and-Tabular Prediction

arXiv: https://arxiv.org/abs/2609.21894 · HTML: https://mlsanity.com/paper/2609.21894/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers](https://mlsanity.com/paper/2309.08532/) (2023)
- [Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering](https://mlsanity.com/paper/2305.03403/) (2023)
- [Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning](https://mlsanity.com/paper/2404.09491/) (2024)
- [Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning](https://mlsanity.com/paper/2406.08527/) (2024)
- [LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers](https://mlsanity.com/paper/2503.14434/) (2025)
- [Large Language Models Are Zero-Shot Text Classifiers](https://mlsanity.com/paper/2312.01044/) (2023)
- [Benchmarking Multimodal AutoML for Tabular Data with Text Fields](https://mlsanity.com/paper/2111.02705/) (2021)

## Built on by (most cited first, 1 of 1)

- [Long Text to Predictive Features: LLM-Guided Blockwise Feature Engineering via Executable Program Search](https://mlsanity.com/paper/2610.12390/) (2026)

## Abstract (arXiv)

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, this error-driven loop accelerates feature discovery by up to 3× compared to unguided search. Empirically, the generated features demonstrate strong multi-view complementarity, strictly outperforming any subset when combined with TF-IDF and dense embeddings. Finally, the framework guarantees instance-level interpretability: the discovered features dominate SHAP importance rankings and provide a fully transparent, semantic audit trail for every prediction.