mlsanityData to 14 Oct 2026

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

arXiv 2511.22858 ↗First posted 28 Nov 2025cs.CL cs.IRcited by 0

On the map: Retrieval-augmented generation → Legal and financial RAG

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation. Builds on 15 of its 19 references that are in the map. First posted on arXiv 28 Nov 2025.

Builds on

15 of 19 references.

References · 15

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022Emergent Abilities of Large Language Modelscited by 2,512
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  4. 2019Language Models as Knowledge Bases?cited by 1,936
  5. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  6. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 810
  7. 2020Estimating Training Data Influence by Tracing Gradient Descentcited by 580
  8. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 269
  9. 2024A Survey on Data Selection for Language Modelscited by 236
  10. 2024Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Toolscited by 176
  11. 2024Reducing hallucination in structured outputs via Retrieval-Augmented Generationcited by 93
  12. 2023Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkerscited by 87
3 more
  1. 2024Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluationcited by 80
  2. 2024Scalable Influence and Fact Tracing for Large Language Model Pretrainingcited by 42
  3. 2025Reducing Hallucinations of Medical Multimodal Large Language Models with Visual Retrieval-Augmented Generationcited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025LRAGE: Legal Retrieval Augmented Generation Evaluation Tool
  2. 2026Pursuing Best Industrial Practices for Retrieval-Augmented Generation in the Medical Domain
  3. 2025All for law and law for all: Adaptive RAG Pipeline for Legal Research
  4. 2025Retrieval Augmented Generation Evaluation for Health Documents
  5. 2025Can LLMs Be Trusted for Evaluating RAG Systems? A Survey of Methods and Datasets
  6. 2025Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMs
  7. 2026Fine-grained Claim-level RAG Benchmark for Law
  8. 2025LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation