2 papers
cs.AI2026
Expert Evaluation of LLM's Open-Ended Legal Reasoning on the Japanese Bar Exam Writing Task
Jungmin Choi, Keisuke Sakaguchi, Hiroaki Yamada
Large language models (LLMs) have shown strong performance on legal benchmarks, including multiple-choice components of bar exams. However, their capacity for generating open-ended…
cs.CL2025
RAG System for Supporting Japanese Litigation Procedures: Faithful Response Generation Complying with Legal Norms
Yuya Ishihara, Atsushi Keyaki, Hiroaki Yamada +2
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…