@inproceedings{chen-etal-2025-slard,
title = "{SLARD}: A {C}hinese Superior Legal Article Retrieval Dataset",
author = "Chen, Zhe and
Ren, Pengjie and
Sun, Fuhui and
Wang, Xiaoyan and
Li, Yujun and
Zhao, Siwen and
Yang, Tengyi",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.50/",
pages = "740--754",
abstract = "Retrieving superior legal articles involves identifying relevant legal articles that hold higher legal effectiveness. This process is crucial in legislative work because superior legal articles form the legal basis for drafting new laws. However, most existing legal information retrieval research focuses on retrieving legal documents, with limited research on retrieving superior legal articles. This gap restricts the digitization of legislative work. To advance research in this area, we propose SLARD: A Chinese Superior Legal Article Retrieval Dataset, which filters 2,627 queries and 9,184 candidates from over 4.3 million effective Chinese regulations, covering 32 categories, such as environment, agriculture, and water resources. Each query is manually annotated, and the candidates include superior articles at both the provincial and national levels. We conducted detailed experiments and analyses on the dataset and found that existing retrieval methods struggle to achieve ideal results. The best method achieved a R@1 of only 0.4719. Additionally, we found that existing large language models (LLMs) lack prior knowledge of the content of superior legal articles. This indicates the necessity for further exploration and research in this field."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2025-slard">
<titleInfo>
<title>SLARD: A Chinese Superior Legal Article Retrieval Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhe</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengjie</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuhui</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yujun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siwen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tengyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Retrieving superior legal articles involves identifying relevant legal articles that hold higher legal effectiveness. This process is crucial in legislative work because superior legal articles form the legal basis for drafting new laws. However, most existing legal information retrieval research focuses on retrieving legal documents, with limited research on retrieving superior legal articles. This gap restricts the digitization of legislative work. To advance research in this area, we propose SLARD: A Chinese Superior Legal Article Retrieval Dataset, which filters 2,627 queries and 9,184 candidates from over 4.3 million effective Chinese regulations, covering 32 categories, such as environment, agriculture, and water resources. Each query is manually annotated, and the candidates include superior articles at both the provincial and national levels. We conducted detailed experiments and analyses on the dataset and found that existing retrieval methods struggle to achieve ideal results. The best method achieved a R@1 of only 0.4719. Additionally, we found that existing large language models (LLMs) lack prior knowledge of the content of superior legal articles. This indicates the necessity for further exploration and research in this field.</abstract>
<identifier type="citekey">chen-etal-2025-slard</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.50/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>740</start>
<end>754</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SLARD: A Chinese Superior Legal Article Retrieval Dataset
%A Chen, Zhe
%A Ren, Pengjie
%A Sun, Fuhui
%A Wang, Xiaoyan
%A Li, Yujun
%A Zhao, Siwen
%A Yang, Tengyi
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F chen-etal-2025-slard
%X Retrieving superior legal articles involves identifying relevant legal articles that hold higher legal effectiveness. This process is crucial in legislative work because superior legal articles form the legal basis for drafting new laws. However, most existing legal information retrieval research focuses on retrieving legal documents, with limited research on retrieving superior legal articles. This gap restricts the digitization of legislative work. To advance research in this area, we propose SLARD: A Chinese Superior Legal Article Retrieval Dataset, which filters 2,627 queries and 9,184 candidates from over 4.3 million effective Chinese regulations, covering 32 categories, such as environment, agriculture, and water resources. Each query is manually annotated, and the candidates include superior articles at both the provincial and national levels. We conducted detailed experiments and analyses on the dataset and found that existing retrieval methods struggle to achieve ideal results. The best method achieved a R@1 of only 0.4719. Additionally, we found that existing large language models (LLMs) lack prior knowledge of the content of superior legal articles. This indicates the necessity for further exploration and research in this field.
%U https://aclanthology.org/2025.coling-main.50/
%P 740-754
Markdown (Informal)
[SLARD: A Chinese Superior Legal Article Retrieval Dataset](https://aclanthology.org/2025.coling-main.50/) (Chen et al., COLING 2025)
ACL
- Zhe Chen, Pengjie Ren, Fuhui Sun, Xiaoyan Wang, Yujun Li, Siwen Zhao, and Tengyi Yang. 2025. SLARD: A Chinese Superior Legal Article Retrieval Dataset. In Proceedings of the 31st International Conference on Computational Linguistics, pages 740–754, Abu Dhabi, UAE. Association for Computational Linguistics.