STARD: A Chinese Statute Retrieval Dataset with Real Queries Issued by Non-professionals

TL;DR

The paper introduces STARD, a Chinese statute retrieval dataset based on real non-professional queries, highlighting the challenges and gaps in current retrieval methods for practical legal applications.

Contribution

It provides a new dataset capturing real-world non-professional legal queries and evaluates existing retrieval methods, revealing their limitations on such complex queries.

Findings

Existing retrieval methods perform poorly on real non-professional queries.

The best retrieval approach achieves only 90.7% Recall@100.

The dataset highlights the need for improved retrieval techniques for practical legal use.

Abstract

Statute retrieval aims to find relevant statutory articles for specific queries. This process is the basis of a wide range of legal applications such as legal advice, automated judicial decisions, legal document drafting, etc. Existing statute retrieval benchmarks focus on formal and professional queries from sources like bar exams and legal case documents, thereby neglecting non-professional queries from the general public, which often lack precise legal terminology and references. To address this gap, we introduce the STAtute Retrieval Dataset (STARD), a Chinese dataset comprising 1,543 query cases collected from real-world legal consultations and 55,348 candidate statutory articles. Unlike existing statute retrieval datasets, which primarily focus on professional legal queries, STARD captures the complexity and diversity of real queries from the general public. Through a comprehensive evaluation of various retrieval baselines, we reveal that existing retrieval approaches all fall short of these real queries issued by non-professional users. The best method only achieves a Recall@100 of 0.907, suggesting the necessity for further exploration and additional research in this area. All the codes and datasets are available at: https://github.com/oneal2000/STARD/tree/main