Saved in:
Bibliographic Details
Main Authors: Li, Jianhao, Xiu, Xianchao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.24157
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917137685151744
author Li, Jianhao
Xiu, Xianchao
author_facet Li, Jianhao
Xiu, Xianchao
contents Recent advances in large language models (LLMs) have provided new opportunities for decision-making, particularly in the task of automated feature selection. In this paper, we first comprehensively evaluate LLM-based feature selection methods, covering the state-of-the-art DeepSeek-R1, GPT-o3-mini, and GPT-4.5. Then, we propose a new hybrid strategy called LLM4FS that integrates LLMs with traditional data-driven methods. Specifically, input data samples into LLMs, and directly call traditional data-driven techniques such as random forest and forward sequential selection. Notably, our analysis reveals that the hybrid strategy leverages the contextual understanding of LLMs and the high statistical reliability of traditional data-driven methods to achieve excellent feature selection performance, even surpassing LLMs and traditional data-driven methods. Finally, we point out the limitations of its application in decision-making. Our code is available at https://github.com/xianchaoxiu/LLM4FS.
format Preprint
id arxiv_https___arxiv_org_abs_2503_24157
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM4FS: Leveraging Large Language Models for Feature Selection
Li, Jianhao
Xiu, Xianchao
Machine Learning
Recent advances in large language models (LLMs) have provided new opportunities for decision-making, particularly in the task of automated feature selection. In this paper, we first comprehensively evaluate LLM-based feature selection methods, covering the state-of-the-art DeepSeek-R1, GPT-o3-mini, and GPT-4.5. Then, we propose a new hybrid strategy called LLM4FS that integrates LLMs with traditional data-driven methods. Specifically, input data samples into LLMs, and directly call traditional data-driven techniques such as random forest and forward sequential selection. Notably, our analysis reveals that the hybrid strategy leverages the contextual understanding of LLMs and the high statistical reliability of traditional data-driven methods to achieve excellent feature selection performance, even surpassing LLMs and traditional data-driven methods. Finally, we point out the limitations of its application in decision-making. Our code is available at https://github.com/xianchaoxiu/LLM4FS.
title LLM4FS: Leveraging Large Language Models for Feature Selection
topic Machine Learning
url https://arxiv.org/abs/2503.24157