RAG System for Supporting Japanese Litigation Procedures: Faithful Response Generation Complying with Legal Norms

TL;DR

This paper proposes a RAG-based language model system designed to support Japanese litigation procedures by ensuring responses are faithful, legally compliant, and contextually relevant, addressing specific legal and ethical constraints.

Contribution

It introduces a novel RAG system tailored for legal contexts that enforces strict adherence to legal norms and proper referencing, which is a significant advancement over generic RAG implementations.

Findings

Designed a retrieval module that respects legal norms and privacy constraints.

Ensured generated responses are faithful to retrieved context.

Implemented timestamp referencing for external knowledge.

Abstract

This study discusses the essential components that a Retrieval-Augmented Generation (RAG)-based LLM system should possess in order to support Japanese medical litigation procedures complying with legal norms. In litigation, expert commissioners, such as physicians, architects, accountants, and engineers, provide specialized knowledge to help judges clarify points of dispute. When considering the substitution of these expert roles with a RAG-based LLM system, the constraint of strict adherence to legal norms is imposed. Specifically, three requirements arise: (1) the retrieval module must retrieve appropriate external knowledge relevant to the disputed issues in accordance with the principle prohibiting the use of private knowledge, (2) the responses generated must originate from the context provided by the RAG and remain faithful to that context, and (3) the retrieval module must reference external knowledge with appropriate timestamps corresponding to the issues at hand. This paper discusses the design of a RAG-based LLM system that satisfies these requirements.