用提示工程+多维知识图谱提升法律纠纷分析能力
An Integrated Framework of Prompt Engineering and Multidimensional Knowledge Graphs for Legal Dispute Analysis
- 分三阶段提示结构引导推理，三层知识图谱整合法律知识
- 准确率提升29.5%-39.7%，敏感度提高11.1%-11.3%
- 适合智能法律助手研发者与司法智能化研究者
法律纠纷分析对智能法律辅助系统至关重要。当前大模型在理解复杂法律概念、保持推理一致性及准确引用法律依据方面面临挑战。本文提出融合提示工程与多维知识图谱的集成框架，包含三阶段分层提示结构（任务定义、知识背景、推理引导）和三层知识图谱（法律本体、表示、实例层）。同时设计四种支持方法实现精准法律概念检索：直接代码匹配、语义向量相似性、本体路径推理与词法切分。大量测试表明，该框架使敏感度提升11.1%-11.3%，特异性提高5.4%-6.0%，引用准确率提升29.5%-39.7%。结果显著改善了法律分析质量与司法逻辑理解，为智能法律辅助系统提供新方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。