@inproceedings{shannon-etal-2026-sg,
title = "{SG}-{L}egal{C}ite: A Principle-Augmented Benchmark for Legal Citation Retrieval in {S}ingapore Law",
author = "Shannon, Lee Yueh Ern and
Feng, Kaidong and
Du, Yingpeng and
Chloe, Lee En Jia and
Sun, Zhu",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.80/",
pages = "1746--1766",
ISBN = "979-8-89176-439-2",
abstract = "Legal citation in common-law systems depends not only on factual similarity, but also on the legal principle for which a precedent is invoked. However, existing benchmarks for legal citation retrieval use case facts, citation context or full judgments as inputs, where the governing legal principle is often missing or only implicitly expressed and entangled with broader context. As a result, models may retrieve precedents that are factually similar yet doctrinally irrelevant. This limitation is particularly consequential in Singapore, where the legal system has evolved independently: only domestic precedents are binding, while foreign authorities serve merely as persuasive references. Thus, we propose a new retrieval paradigm that ranks cited cases based on queries integrating case facts and explicit legal principle, inspired by the real-world legal reasoning workflows. To support this paradigm, we further introduce SG-LegalCite, a dataset of 100,890 case{--}principle pairs extracted from 8,523 Singapore Supreme Court judgments spanning 2000{--}2025. Experiments across 11 baselines demonstrate the effectiveness of our principle-augmented retrieval paradigm, showing that explicit legal principles provide strong discriminative signals for legal citation retrieval. Our dataset and code is at https://github.com/ShannonLeeYuehErn/SG-LegalCite"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shannon-etal-2026-sg">
<titleInfo>
<title>SG-LegalCite: A Principle-Augmented Benchmark for Legal Citation Retrieval in Singapore Law</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lee</namePart>
<namePart type="given">Yueh</namePart>
<namePart type="given">Ern</namePart>
<namePart type="family">Shannon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaidong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingpeng</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lee</namePart>
<namePart type="given">En</namePart>
<namePart type="given">Jia</namePart>
<namePart type="family">Chloe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Legal citation in common-law systems depends not only on factual similarity, but also on the legal principle for which a precedent is invoked. However, existing benchmarks for legal citation retrieval use case facts, citation context or full judgments as inputs, where the governing legal principle is often missing or only implicitly expressed and entangled with broader context. As a result, models may retrieve precedents that are factually similar yet doctrinally irrelevant. This limitation is particularly consequential in Singapore, where the legal system has evolved independently: only domestic precedents are binding, while foreign authorities serve merely as persuasive references. Thus, we propose a new retrieval paradigm that ranks cited cases based on queries integrating case facts and explicit legal principle, inspired by the real-world legal reasoning workflows. To support this paradigm, we further introduce SG-LegalCite, a dataset of 100,890 case–principle pairs extracted from 8,523 Singapore Supreme Court judgments spanning 2000–2025. Experiments across 11 baselines demonstrate the effectiveness of our principle-augmented retrieval paradigm, showing that explicit legal principles provide strong discriminative signals for legal citation retrieval. Our dataset and code is at https://github.com/ShannonLeeYuehErn/SG-LegalCite</abstract>
<identifier type="citekey">shannon-etal-2026-sg</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.80/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1746</start>
<end>1766</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SG-LegalCite: A Principle-Augmented Benchmark for Legal Citation Retrieval in Singapore Law
%A Shannon, Lee Yueh Ern
%A Feng, Kaidong
%A Du, Yingpeng
%A Chloe, Lee En Jia
%A Sun, Zhu
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F shannon-etal-2026-sg
%X Legal citation in common-law systems depends not only on factual similarity, but also on the legal principle for which a precedent is invoked. However, existing benchmarks for legal citation retrieval use case facts, citation context or full judgments as inputs, where the governing legal principle is often missing or only implicitly expressed and entangled with broader context. As a result, models may retrieve precedents that are factually similar yet doctrinally irrelevant. This limitation is particularly consequential in Singapore, where the legal system has evolved independently: only domestic precedents are binding, while foreign authorities serve merely as persuasive references. Thus, we propose a new retrieval paradigm that ranks cited cases based on queries integrating case facts and explicit legal principle, inspired by the real-world legal reasoning workflows. To support this paradigm, we further introduce SG-LegalCite, a dataset of 100,890 case–principle pairs extracted from 8,523 Singapore Supreme Court judgments spanning 2000–2025. Experiments across 11 baselines demonstrate the effectiveness of our principle-augmented retrieval paradigm, showing that explicit legal principles provide strong discriminative signals for legal citation retrieval. Our dataset and code is at https://github.com/ShannonLeeYuehErn/SG-LegalCite
%U https://aclanthology.org/2026.aacl-long.80/
%P 1746-1766
Markdown (Informal)
[SG-LegalCite: A Principle-Augmented Benchmark for Legal Citation Retrieval in Singapore Law](https://aclanthology.org/2026.aacl-long.80/) (Shannon et al., AACL-IJCNLP 2026)
ACL
- Lee Yueh Ern Shannon, Kaidong Feng, Yingpeng Du, Lee En Jia Chloe, and Zhu Sun. 2026. SG-LegalCite: A Principle-Augmented Benchmark for Legal Citation Retrieval in Singapore Law. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1746–1766, Hengqin, China. Association for Computational Linguistics.