An Integrated Framework of Prompt Engineering and Multidimensional Knowledge Graphs for Legal Dispute Analysis

TL;DR

This paper introduces an integrated framework combining prompt engineering and multidimensional knowledge graphs to enhance legal dispute analysis by large language models, significantly improving accuracy, reasoning, and citation reliability.

Contribution

It proposes a novel hierarchical prompt structure and a three-layer knowledge graph, along with four retrieval methods, to improve legal understanding in LLMs, which is a new approach in legal AI research.

Findings

Sensitivity increased by 11.1%-11.3%

Specificity increased by 5.4%-6.0%

Citation accuracy improved by 29.5%-39.7%

Abstract

Legal dispute analysis is crucial for intelligent legal assistance systems. However, current LLMs face significant challenges in understanding complex legal concepts, maintaining reasoning consistency, and accurately citing legal sources. This research presents a framework combining prompt engineering with multidimensional knowledge graphs to improve LLMs' legal dispute analysis. Specifically, the framework includes a three-stage hierarchical prompt structure (task definition, knowledge background, reasoning guidance) along with a three-layer knowledge graph (legal ontology, representation, instance layers). Additionally, four supporting methods enable precise legal concept retrieval: direct code matching, semantic vector similarity, ontology path reasoning, and lexical segmentation. Through extensive testing, results show major improvements: sensitivity increased by 11.1%-11.3%, specificity by 5.4%-6.0%, and citation accuracy by 29.5%-39.7%. As a result, the framework provides better legal analysis and understanding of judicial logic, thus offering a new technical method for intelligent legal assistance systems.