JUREX-4E: Juridical Expert-Annotated Four-Element Knowledge Base for Legal Reasoning

2025-02-24

AI Summary

Existing large language models (LLMs) rely on implicit internal knowledge for legal tasks, rendering them ill-suited for systematic modeling of the four constitutive elements of criminal liability—perpetrator, object, subjective aspect, and objective aspect—leading to incomplete element coverage and insufficient doctrinal authority. Method: We construct the first expert-annotated, structured knowledge base explicitly encoding these four elements across 155 criminal offenses, integrating juristic interpretation theory with a hierarchical annotation framework to ensure statutory fidelity and interpretive diversity. Our methodology comprises legal ontology modeling, multi-source textual parsing, offense-element mapping, and comparative evaluation of semantically similar offenses. Contribution/Results: Empirical evaluation demonstrates significant improvements in LLM performance on fine-grained offense distinction tasks, alongside enhanced relevance and explainability in legal case retrieval. The knowledge base exhibits high quality, verifiability, traceability, and strong downstream generalization capability.

Technology Category

• Knowledge Representation and Reasoning: Description Logics
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The Four-Element Theory is a fundamental framework in criminal law, defining the constitution of crime through four dimensions: Subject, Object, Subjective aspect, and Objective aspect. This theory is widely referenced in legal reasoning, and many Large Language Models (LLMs) attempt to incorporate it when handling legal tasks. However, current approaches rely on LLMs' internal knowledge to incorporate this theory, often lacking completeness and representativeness. To address this limitation, we introduce JUREX-4E, an expert-annotated knowledge base covering 155 criminal charges. It is structured through a progressive hierarchical annotation framework that prioritizes legal source validity and employs diverse legal interpretation methods to ensure comprehensiveness and authority. We evaluate JUREX-4E on the Similar Charge Distinction task and apply it to Legal Case Retrieval, demonstrating its effectiveness in improving LLM performance. Experimental results validate the high quality of JUREX-4E and its substantial impact on downstream legal tasks, underscoring its potential for advancing legal AI applications. Code: https://github.com/THUlawtech/JUREX

Problem

• Enhance legal reasoning in LLMs
• Address incompleteness in Four-Element Theory
• Improve performance in legal tasks

Innovation

• Expert-annotated legal knowledge base
• Hierarchical annotation framework
• Enhances LLM legal task performance