支持日本诉讼程序的RAG系统：遵循法律规范的忠实响应生成 (RAG System for Supporting Japanese Litigation Procedures: Faithful Response Generation Complying with Legal Norms)

from arxiv, This is a preprint version of a paper reviewed and accepted at BREV-RAG 2025: Beyond Relevance-based EValuation of RAG Systems, a SIGIR-AP 2025 workshop

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.

翻译：本研究探讨了基于检索增强生成（RAG）的大型语言模型系统为支持遵循法律规范的日本医疗诉讼程序所应具备的核心要素。在诉讼中，专家委员（如医师、建筑师、会计师和工程师）提供专业知识以协助法官厘清争议点。当考虑以基于RAG的LLM系统替代这些专家角色时，必须施加严格遵守法律规范的约束。具体而言，系统需满足三项要求：（1）检索模块必须依据禁止使用私人知识的原则，检索与争议问题相关的适当外部知识；（2）生成的响应必须源自RAG提供的上下文，并忠实于该上下文；（3）检索模块引用外部知识时需具备与所涉问题对应的适当时间戳。本文讨论了满足这些要求的基于RAG的LLM系统设计方案。