Leverage Knowledge Graph and Large Language Model for Law Article Recommendation: A Case Study of Chinese Criminal Law

2024-10-07

arXiv.org

AI Summary

Grassroots courts face severe case backlogs due to chronic understaffing and heavy reliance on manual, experience-based adjudication. Method: This paper proposes a novel legal article recommendation paradigm integrating knowledge graphs with large language models (LLMs). We introduce the Case-Enhanced Legal Article Knowledge Graph (CLAKG), which unifies statutory provisions, judicial precedents, and multi-dimensional semantic relations; further, we design an LLM-driven automated graph construction and closed-loop reasoning recommendation framework, incorporating prompt engineering, supervised fine-tuning, and precedent–statute semantic matching. Results: Evaluated on criminal judgment data from China Judgments Online, our approach improves legal article recommendation accuracy from 0.549 to 0.694—significantly outperforming existing baselines. To our knowledge, this is the first work to tightly integrate case-enhanced knowledge graphs with LLM-based closed-loop reasoning, offering a practical, deployable solution for enhancing judicial efficiency in resource-constrained, low-AI-assistance environments.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Automated Reasoning and Theorem Proving

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Improve court efficiency by reducing case backlogs
• Enhance law article recommendation accuracy using KG and LLM
• Automate construction of Case-Enhanced Law Article Knowledge Graph

Innovation

• Utilizes Knowledge Graph for law article storage
• Employs Large Language Model for automation
• Improves recommendation accuracy significantly