paper-with-me

홈 › Papers

Expert Evaluation of LLM's Open-Ended Legal Reasoning on the Japanese Bar Exam Writing Task

2026-04-26 · Jungmin Choi, Keisuke Sakaguchi, Hiroaki Yamada arxiv

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 legal reasoning in realistic scenarios remains insufficiently explored. Notably, to our best knowledge, there are no prior studies or datasets addressing this issue in the Japanese context. This study presents the first dataset designed to evaluate the open-ended legal reasoning performance of LLMs within the Japanese jurisdiction. The dataset is based on the writing component of the Japanese bar examination, which requires examinees to identify multiple legal issues from long narratives and to construct structured legal arguments in free text format. Our key contribution is the manual evaluation of LLMs' generated responses by legal experts, which reveals limitations and challenges in legal reasoning. Moreover, we conducted a manual analysis of hallucinations to characterize when and how the models introduce content not supported by precedent or law. Our real exam questions, model-generated responses, and expert evaluations reveal the milestones of current LLMs in the Japanese legal domain. Our dataset and relevant resources will be available online.

📄 PDF Abstract BibTeX arXiv:2604.23730

Code (0)

등록된 구현이 없습니다.

Tasks

Legal Reasoning

Similar Papers 제목 키워드 기반

LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks

2026-06-08 · Yifan Chen, Haitao Li, Yiran Hu, Kaisong Song 외 arxiv

As large language models (LLMs) are increasingly applied to real-world legal tasks, evaluating the reliability of their open-ended legal responses has become essential. These tasks require context-sensitive answers and a…

Legal Reasoning

LEXam: Benchmarking Legal Reasoning on 340 Law Exams

2025-05-19 · Yu Fan, Jingwei Ni, Jakob Merane, Etienne Salimbeni 외

Long-form legal reasoning remains a key challenge for large language models (LLMs) in spite of recent advances in test-time scaling. We introduce LEXam, a novel benchmark derived from 340 law exams spanning 116 law schoo…

BenchmarkingLegal ReasoningMultiple-choice

PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning

2025-11-14 · Afra Feyza Akyürek, Advait Gosai, Chen Bo Calvin Zhang, Vipul Gupta 외 arxiv

Frontier model progress is often measured by academic benchmarks, which offer a limited view of performance in real-world professional contexts. Existing evaluations often fail to assess open-ended, economically conseque…

KoBLEX: Open Legal Question Answering with Multi-hop Reasoning

2025-09-01 · Jihyung Lee, Daehui Kim, Seonjeong Hwang, Hyounghun Kim 외 arxiv

Large Language Models (LLM) have achieved remarkable performances in general domains and are now extending into the expert domain of law. Several benchmarks have been proposed to evaluate LLMs' legal capabilities. Howeve…

Question AnsweringLegal Reasoning

A Comprehensive Evaluation of Large Language Models on Legal Judgment Prediction

2023-10-18 · Ruihao Shui, Yixin Cao, Xiang Wang, Tat-Seng Chua

Large language models (LLMs) have demonstrated great potential for domain-specific applications, such as the law domain. However, recent disputes over GPT-4's law evaluation raise questions concerning their performance i…

Information RetrievalLegal ReasoningRetrieval