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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ishihara, Yuya, Keyaki, Atsushi, Yamada, Hiroaki, Ohara, Ryutaro, Sumida, Mihoko
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918221732380672
author Ishihara, Yuya
Keyaki, Atsushi
Yamada, Hiroaki
Ohara, Ryutaro
Sumida, Mihoko
author_facet Ishihara, Yuya
Keyaki, Atsushi
Yamada, Hiroaki
Ohara, Ryutaro
Sumida, Mihoko
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22858
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RAG System for Supporting Japanese Litigation Procedures: Faithful Response Generation Complying with Legal Norms
Ishihara, Yuya
Keyaki, Atsushi
Yamada, Hiroaki
Ohara, Ryutaro
Sumida, Mihoko
Computation and Language
Information Retrieval
68T50
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.
title RAG System for Supporting Japanese Litigation Procedures: Faithful Response Generation Complying with Legal Norms
topic Computation and Language
Information Retrieval
68T50
url https://arxiv.org/abs/2511.22858