paper-with-me

홈 › Papers

Exploring Large Language Models for Feature Selection: A Data-centric Perspective

2024-08-21 · Dawei Li, Zhen Tan, Huan Liu

The rapid advancement of Large Language Models (LLMs) has significantly influenced various domains, leveraging their exceptional few-shot and zero-shot learning capabilities. In this work, we aim to explore and understand the LLMs-based feature selection methods from a data-centric perspective. We begin by categorizing existing feature selection methods with LLMs into two groups: data-driven feature selection which requires numerical values of samples to do statistical inference and text-based feature selection which utilizes prior knowledge of LLMs to do semantical associations using descriptive context. We conduct experiments in both classification and regression tasks with LLMs in various sizes (e.g., GPT-4, ChatGPT and LLaMA-2). Our findings emphasize the effectiveness and robustness of text-based feature selection methods and showcase their potentials using a real-world medical application. We also discuss the challenges and future opportunities in employing LLMs for feature selection, offering insights for further research and development in this emerging field.

📄 PDF Abstract BibTeX arXiv:2408.12025

Code (0)

등록된 구현이 없습니다.

Tasks

Descriptivefeature selectionZero-Shot Learning

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Multi-Head Attention 설명 없음
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Boosting for Efficient Model Selection for Syntactic Parsing

2016-12-01 · COLING 2016 12 · Rachel Bawden, Beno{\^\i}t Crabb{\'e}

We present an efficient model selection method using boosting for transition-based constituency parsing. It is designed for exploring a high-dimensional search space, defined by a large set of feature templates, as for e…

Constituency ParsingmodelModel Selection

Exploring Large Feature Spaces with Hierarchical Multiple Kernel Learning

2008-12-01 · NeurIPS 2008 12 · Francis R. Bach

For supervised and unsupervised learning, positive definite kernels allow to use large and potentially infinite dimensional feature spaces with a computational cost that only depends on the number of observations. This i…

Variable Selection

Exploring Large Feature Spaces with Hierarchical Multiple Kernel Learning

2008-09-09 · Francis Bach

For supervised and unsupervised learning, positive definite kernels allow to use large and potentially infinite dimensional feature spaces with a computational cost that only depends on the number of observations. This i…

Variable Selection

Exploring Imbalanced Annotations for Effective In-Context Learning

2025-02-06 · Hongfu Gao, Feipeng Zhang, Hao Zeng, Deyu Meng 외

Large language models (LLMs) have shown impressive performance on downstream tasks through in-context learning (ICL), which heavily relies on the demonstrations selected from annotated datasets. However, these datasets o…

In-Context Learning

Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Models

2024-06-05 · Sheng-Lun Wei, Cheng-Kuang Wu, Hen-Hsen Huang, Hsin-Hsi Chen

In this paper, we investigate the phenomena of "selection biases" in Large Language Models (LLMs), focusing on problems where models are tasked with choosing the optimal option from an ordered sequence. We delve into bia…

Decision MakingSensitivity