arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.12464cs.LGcs.AIcs.CL
收藏

面向少样本分类的表格数据序列化改进方法:基于大型语言模型

Towards Better Serialization of Tabular Data for Few-shot Classification with Large Language Models

Carnegie Mellon University(卡内基梅隆大学)

Sukriti Jaitly, Tanay Shah, Ashish Shugani, Razik Singh Grewal

AI总结:

本研究提出基于LLM的表格数据分类高效框架,引入LaTeX等三种序列化技术,显著提升领域数据集处理性能,在准确性和效率上优于传统模型。

摘要:

我们提出了一项关于将大型语言模型(LLMs)集成到表格数据分类中的研究,重点强调一种高效框架。在TabLLM(arXiv:2210.10723)现有工作的基础上,我们引入了三种新颖的序列化技术,其中包括突出的LaTeX序列化方法。该方法显著提升了LLMs在处理领域特定数据集时的性能,其优势在于内存效率高且能充分利用复杂数据结构。通过大量实验,包括特征组合和特征重要性等多种序列化方法,我们证明了我们的工作在准确性和效率上优于传统模型。

英文摘要:

We present a study on the integration of Large Language Models (LLMs) in tabular data classification, emphasizing an efficient framework. Building upon existing work done in TabLLM (arXiv:2210.10723), we introduce three novel serialization techniques, including the standout LaTeX serialization method. This method significantly boosts the performance of LLMs in processing domain-specific datasets, Our method stands out for its memory efficiency and ability to fully utilize complex data structures. Through extensive experimentation, including various serialization approaches like feature combination and importance, we demonstrate our work's superiority in accuracy and efficiency over traditional models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑