Saved in:
Bibliographic Details
Main Authors: Chen, Yongming, Chen, Miner, Zhu, Ye, Pei, Juan, Chen, Siyu, Zhou, Yu, Wang, Yi, Zhou, Yifan, Li, Hao, Zhang, Songan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.04949
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918366866833408
author Chen, Yongming
Chen, Miner
Zhu, Ye
Pei, Juan
Chen, Siyu
Zhou, Yu
Wang, Yi
Zhou, Yifan
Li, Hao
Zhang, Songan
author_facet Chen, Yongming
Chen, Miner
Zhu, Ye
Pei, Juan
Chen, Siyu
Zhou, Yu
Wang, Yi
Zhou, Yifan
Li, Hao
Zhang, Songan
contents Judicial efficiency is critical to social stability. However, in many countries worldwide, grassroots courts face substantial case backlogs, and judicial decisions remain heavily dependent on judges' cognitive efforts, with insufficient intelligent tools to enhance efficiency. To address this issue, we propose a highly efficient law article recommendation approach combining a Knowledge Graph (KG) and a Large Language Model (LLM). First, we construct a Case-Enhanced Law Article Knowledge Graph (CLAKG) to store current law articles, historical case information, and their interconnections, alongside an LLM-based automated construction method. Building on this, we propose a closed-loop law article recommendation framework integrating graph embedding-based retrieval and KG-grounded LLM reasoning. Experiments on judgment documents from China Judgments Online demonstrate that our method boosts law article recommendation accuracy from 0.549 to 0.694, outperforming strong baselines significantly. To support reproducibility and future research, all source code and processed datasets are publicly available on GitHub (see Data Availability Statement).
format Preprint
id arxiv_https___arxiv_org_abs_2410_04949
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Leverage Knowledge Graph and Large Language Model for Law Article Recommendation: A Case Study of Chinese Criminal Law
Chen, Yongming
Chen, Miner
Zhu, Ye
Pei, Juan
Chen, Siyu
Zhou, Yu
Wang, Yi
Zhou, Yifan
Li, Hao
Zhang, Songan
Information Retrieval
Artificial Intelligence
Judicial efficiency is critical to social stability. However, in many countries worldwide, grassroots courts face substantial case backlogs, and judicial decisions remain heavily dependent on judges' cognitive efforts, with insufficient intelligent tools to enhance efficiency. To address this issue, we propose a highly efficient law article recommendation approach combining a Knowledge Graph (KG) and a Large Language Model (LLM). First, we construct a Case-Enhanced Law Article Knowledge Graph (CLAKG) to store current law articles, historical case information, and their interconnections, alongside an LLM-based automated construction method. Building on this, we propose a closed-loop law article recommendation framework integrating graph embedding-based retrieval and KG-grounded LLM reasoning. Experiments on judgment documents from China Judgments Online demonstrate that our method boosts law article recommendation accuracy from 0.549 to 0.694, outperforming strong baselines significantly. To support reproducibility and future research, all source code and processed datasets are publicly available on GitHub (see Data Availability Statement).
title Leverage Knowledge Graph and Large Language Model for Law Article Recommendation: A Case Study of Chinese Criminal Law
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2410.04949