Leverage Knowledge Graph and Large Language Model for Law Article Recommendation: A Case Study of Chinese Criminal Law
Yongming Chen, Miner Chen, Ye Zhu, Juan Pei, Siyu Chen, Yu Zhou, Yi Wang, Yifan Zhou, Hao Li, Songan Zhang
TL;DR
elsarticle.cls is a LaTeX document class designed for formatting submissions to Elsevier journals, built on article.cls to minimize package conflicts and to work with a standard set of packages such as natbib, geometry, and graphicx. It supports flexible frontmatter, multiple formatting models (preprint and final formats for various models), and easy customization of article layout, including two-column formats. The document also contrasts elsarticle.cls with the older elsart.cls, highlighting reduced clashes, enhanced citation handling, and streamlined frontmatter management. Practical installation guidance is provided via Elsevier resources and CTAN, detailing the generation of the class file from source and integration into the TeX distribution. Overall, the class aims to simplify high-quality manuscript preparation and ensure compatibility across common TeX environments.
Abstract
Court efficiency is vital for social stability. However, in most countries around the world, the grassroots courts face case backlogs, with decisions relying heavily on judicial personnel's cognitive labor, lacking intelligent tools to improve efficiency. To address this issue, we propose an efficient law article recommendation approach utilizing a Knowledge Graph (KG) and a Large Language Model (LLM). Firstly, we propose a Case-Enhanced Law Article Knowledge Graph (CLAKG) as a database to store current law statutes, historical case information, and correspondence between law articles and historical cases. Additionally, we introduce an automated CLAKG construction method based on LLM. On this basis, we propose a closed-loop law article recommendation method. Finally, through a series of experiments using judgment documents from the website "China Judgements Online", we have improved the accuracy of law article recommendation in cases from 0.549 to 0.694, demonstrating that our proposed method significantly outperforms baseline approaches.