用大模型生成特征值，零样本建原型，不训练也能做表格分类。
LLM Empowered Prototype Learning for Zero and Few-Shot Tasks on Tabular Data
- 大模型凭描述生成特征值，无须样本构建原型。
- 零样本准确率超基线15.6%，少样本提升显著。
- 适合无数据或数据稀缺的表格任务场景。
大型语言模型（LLMs）在表格数据建模中的潜力正受到广泛关注。然而，在少样本甚至零样本情况下有效利用先进LLMs仍具挑战。为此，我们提出一种基于LLM的原型估计框架用于表格学习。核心思想是通过仅依赖任务和特征描述的无样本提示（example-free prompt），让LLM生成特征值，从而无需训练即可构建零样本原型，并可通过融合少量样本进一步优化，避免训练分类器或微调LLMs。得益于无样本提示与原型估计，该方法突破了传统以样本为基础提示的限制，具有可扩展性和鲁棒性。大量实验表明，该方法在零样本和少样本表格学习中均表现出色。
原文摘要 · Abstract (English)
Recent breakthroughs in large language models (LLMs) have opened the door to in-depth investigation of their potential in tabular data modeling. However, effectively utilizing advanced LLMs in few-shot and even zero-shot scenarios is still challenging. To this end, we propose a novel LLM-based prototype estimation framework for tabular learning. Our key idea is to query the LLM to generate feature values based example-free prompt, which solely relies on task and feature descriptions. With the feature values generated by LLM, we can build a zero-shot prototype in a training-free manner, which can be further enhanced by fusing few-shot samples, avoiding training a classifier or finetuning the LLMs. Thanks to the example-free prompt and prototype estimation, ours bypasses the constraints brought by the example-based prompt, providing a scalable and robust framework. Extensive experiments demonstrate the effectiveness of ours in zero and few-shot tabular learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。