Salvato in:
Dettagli Bibliografici
Autori principali: Lim, Yebin, Yoon, Susik
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.25207
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912615322615808
author Lim, Yebin
Yoon, Susik
author_facet Lim, Yebin
Yoon, Susik
contents Recent advancements in large language models (LLMs) have shown promise in feature engineering for tabular data, but concerns about their reliability persist, especially due to variability in generated outputs. We introduce a multi-level diagnosis and evaluation framework to assess the robustness of LLMs in feature engineering across diverse domains, focusing on the three main factors: key variables, relationships, and decision boundary values for predicting target classes. We demonstrate that the robustness of LLMs varies significantly over different datasets, and that high-quality LLM-generated features can improve few-shot prediction performance by up to 10.52%. This work opens a new direction for assessing and enhancing the reliability of LLM-driven feature engineering in various domains.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25207
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-level Diagnosis and Evaluation for Robust Tabular Feature Engineering with Large Language Models
Lim, Yebin
Yoon, Susik
Machine Learning
Artificial Intelligence
Recent advancements in large language models (LLMs) have shown promise in feature engineering for tabular data, but concerns about their reliability persist, especially due to variability in generated outputs. We introduce a multi-level diagnosis and evaluation framework to assess the robustness of LLMs in feature engineering across diverse domains, focusing on the three main factors: key variables, relationships, and decision boundary values for predicting target classes. We demonstrate that the robustness of LLMs varies significantly over different datasets, and that high-quality LLM-generated features can improve few-shot prediction performance by up to 10.52%. This work opens a new direction for assessing and enhancing the reliability of LLM-driven feature engineering in various domains.
title Multi-level Diagnosis and Evaluation for Robust Tabular Feature Engineering with Large Language Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.25207