Authors: Yongming Chen, Miner Chen, Ye Zhu, Juan Pei, Siyu Chen, Yu Zhou, Yi Wang, Yifan Zhou, Hao Li, Songan Zhang

Published on: October 07, 2024

Impact Score: 7.8

Arxiv code: Arxiv:2410.04949

Summary

• What is new: This research introduces a new approach for recommending law articles using a Knowledge Graph (KG) and a Large Language Model (LLM).
• Why this is important: Grassroots courts often face case backlogs and rely heavily on judicial personnel’s cognitive labor without adequate intelligent tools to improve efficiency.
• What the research proposes: The proposed solution includes creating a Case-Enhanced Law Article Knowledge Graph (CLAKG) to store law statutes and case information, and an automated method to construct CLAKG using LLM.
• Results: Experiments showed an improvement in the accuracy of law article recommendations from 0.549 to 0.694, indicating a significant enhancement over existing baseline methods.

Technical Details

Technological frameworks used: Knowledge Graph (KG), Large Language Model (LLM)

Models used: Case-Enhanced Law Article Knowledge Graph (CLAKG)

Data used: Judgment documents from ‘China Judgements Online’

Potential Impact

Legal technology companies, judicial systems, and law firms could significantly benefit from the enhanced efficiency provided by the proposed recommendation approach.

Want to implement this idea in a business?

We have generated a startup concept here: Judicial Edge.