用知识图谱增强大模型，提升表格列类型标注准确率
RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge Graph
- 结合预训练参数与非参数知识图谱增强上下文
- 相比纯大模型推理，微调后F1值最高提升0.21
- 适合需要高精度数据标注的智能数据探索场景
作为数据探索与集成的重要环节，列类型标注（CTA）旨在为表格中的列标记一个或多个语义类型。随着大语言模型（LLMs）的发展，研究人员开始探索利用其强大的零样本能力进行CTA。本文在此基础上提出RACOON框架，通过引入知识图谱（KG）来增强提供给大模型的上下文信息，从而提升其在CTA任务上的表现。该方法在生成过程中融合了预训练的参数化知识与非参数化知识，显著提升了模型性能。实验结果表明，RACOON相较于基础的LLM推理，在微平均F1值上最高提升0.21。
原文摘要 · Abstract (English)
As an important component of data exploration and integration, Column Type Annotation (CTA) aims to label columns of a table with one or more semantic types. With the recent development of Large Language Models (LLMs), researchers have started to explore the possibility of using LLMs for CTA, leveraging their strong zero-shot capabilities. In this paper, we build on this promising work and improve on LLM-based methods for CTA by showing how to use a Knowledge Graph (KG) to augment the context information provided to the LLM. Our approach, called RACOON, combines both pre-trained parametric and non-parametric knowledge during generation to improve LLMs' performance on CTA. Our experiments show that RACOON achieves up to a 0.21 micro F-1 improvement compared against vanilla LLM inference.
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。