Large Language Models and Explainable Law: a Hybrid Methodology

TL;DR

This paper proposes a hybrid methodology using large language models to improve the explainability and accessibility of rule-based legal systems, enabling laypeople to perform complex legal tasks through natural language explanations.

Contribution

It introduces a novel approach combining LLMs with rule-based legal systems to translate explanations into natural language and empower non-experts to execute juridical tasks autonomously.

Findings

LLMs can effectively translate rule-based explanations into natural language.

The methodology enables laypeople to perform complex legal comparisons.

The approach enhances transparency and user engagement in legal technology.

Abstract

The paper advocates for LLMs to enhance the accessibility, usage and explainability of rule-based legal systems, contributing to a democratic and stakeholder-oriented view of legal technology. A methodology is developed to explore the potential use of LLMs for translating the explanations produced by rule-based systems, from high-level programming languages to natural language, allowing all users a fast, clear, and accessible interaction with such technologies. The study continues by building upon these explanations to empower laypeople with the ability to execute complex juridical tasks on their own, using a Chain of Prompts for the autonomous legal comparison of different rule-based inferences, applied to the same factual case.