Summary of Exploring Large Language Models For Feature Selection: a Data-centric Perspective, by Dawei Li et al.
Exploring Large Language Models for Feature Selection: A Data-centric Perspective
by Dawei Li, Zhen Tan, Huan Liu
First submitted to arxiv on: 21 Aug 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper explores Large Language Models (LLMs) for feature selection in various domains, leveraging their few-shot and zero-shot learning capabilities. The authors categorize existing methods into data-driven and text-based approaches, and conduct experiments with LLMs of different sizes (GPT-4, ChatGPT, and LLaMA-2). Their findings highlight the effectiveness and robustness of text-based feature selection methods, particularly in a real-world medical application. The paper also discusses challenges and future opportunities for using LLMs for feature selection. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how Large Language Models (LLMs) can be used to help pick important features from data. It talks about two ways this can be done: by looking at numbers (data-driven) or by understanding words (text-based). The researchers test different sizes of LLMs and find that the text-based method works well, especially in a medical example. They also think about what might make it hard to use LLMs for feature selection and where they could go from here. |
Keywords
» Artificial intelligence » Feature selection » Few shot » Gpt » Llama » Zero shot
