@inproceedings{liu-etal-2026-lexpath,
title = "{L}ex{P}ath: A Domain-Oriented Multi-Path Framework for Legal Article Retrieval",
author = "Liu, Weixuan and
Zhuge, Qingfeng and
Chen, Xuyang",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1108/",
pages = "25377--25394",
ISBN = "979-8-89176-459-0",
abstract = "Legal article retrieval is critical for building traceable and reliable legal AI systems, where conclusions must be grounded in specific legal articles. However, existing open-domain retrieval methods rely heavily on surface-level lexical or semantic similarity, making it difficult for them to distinguish legally relevant articles from those that are textually similar but legally inapplicable or misaligned with the user{'}s underlying intent. To bridge this gap, we propose **LexPath**, a domain-oriented multi-path framework comprising a multi-path retrieval module and an intent-aware reranking module. The retrieval module combines two complementary legal-specific paths to collect candidate articles: an IRAC-guided sparse path that expands queries with legally informative keywords, and a structure-guided dense path trained with hard negatives derived from legal hierarchy and citation relations. The reranking module then further refines the candidate ranking by incorporating the intent consistency score between queries and legal articles. We evaluate **LexPath** on three Chinese benchmarks spanning diverse query scenarios, and further assess its cross-jurisdictional applicability on a Japanese benchmark. Experimental results demonstrate that \textsc{LexPath} consistently outperforms lexical, dense, hybrid, and adaptive retrieval-augmented generation (RAG) baselines across the four benchmarks. Ablation studies further verify the effectiveness of each component. The data and code are available at: {\ensuremath{<}}https://github.com/wxliuabigail/LexPath{\ensuremath{>}}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-lexpath">
<titleInfo>
<title>LexPath: A Domain-Oriented Multi-Path Framework for Legal Article Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weixuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingfeng</namePart>
<namePart type="family">Zhuge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuyang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Legal article retrieval is critical for building traceable and reliable legal AI systems, where conclusions must be grounded in specific legal articles. However, existing open-domain retrieval methods rely heavily on surface-level lexical or semantic similarity, making it difficult for them to distinguish legally relevant articles from those that are textually similar but legally inapplicable or misaligned with the user’s underlying intent. To bridge this gap, we propose **LexPath**, a domain-oriented multi-path framework comprising a multi-path retrieval module and an intent-aware reranking module. The retrieval module combines two complementary legal-specific paths to collect candidate articles: an IRAC-guided sparse path that expands queries with legally informative keywords, and a structure-guided dense path trained with hard negatives derived from legal hierarchy and citation relations. The reranking module then further refines the candidate ranking by incorporating the intent consistency score between queries and legal articles. We evaluate **LexPath** on three Chinese benchmarks spanning diverse query scenarios, and further assess its cross-jurisdictional applicability on a Japanese benchmark. Experimental results demonstrate that LexPath consistently outperforms lexical, dense, hybrid, and adaptive retrieval-augmented generation (RAG) baselines across the four benchmarks. Ablation studies further verify the effectiveness of each component. The data and code are available at: \ensuremath<https://github.com/wxliuabigail/LexPath\ensuremath>.</abstract>
<identifier type="citekey">liu-etal-2026-lexpath</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1108/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>25377</start>
<end>25394</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LexPath: A Domain-Oriented Multi-Path Framework for Legal Article Retrieval
%A Liu, Weixuan
%A Zhuge, Qingfeng
%A Chen, Xuyang
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F liu-etal-2026-lexpath
%X Legal article retrieval is critical for building traceable and reliable legal AI systems, where conclusions must be grounded in specific legal articles. However, existing open-domain retrieval methods rely heavily on surface-level lexical or semantic similarity, making it difficult for them to distinguish legally relevant articles from those that are textually similar but legally inapplicable or misaligned with the user’s underlying intent. To bridge this gap, we propose **LexPath**, a domain-oriented multi-path framework comprising a multi-path retrieval module and an intent-aware reranking module. The retrieval module combines two complementary legal-specific paths to collect candidate articles: an IRAC-guided sparse path that expands queries with legally informative keywords, and a structure-guided dense path trained with hard negatives derived from legal hierarchy and citation relations. The reranking module then further refines the candidate ranking by incorporating the intent consistency score between queries and legal articles. We evaluate **LexPath** on three Chinese benchmarks spanning diverse query scenarios, and further assess its cross-jurisdictional applicability on a Japanese benchmark. Experimental results demonstrate that LexPath consistently outperforms lexical, dense, hybrid, and adaptive retrieval-augmented generation (RAG) baselines across the four benchmarks. Ablation studies further verify the effectiveness of each component. The data and code are available at: \ensuremath<https://github.com/wxliuabigail/LexPath\ensuremath>.
%U https://aclanthology.org/2026.emnlp-main.1108/
%P 25377-25394
Markdown (Informal)
[LexPath: A Domain-Oriented Multi-Path Framework for Legal Article Retrieval](https://aclanthology.org/2026.emnlp-main.1108/) (Liu et al., EMNLP 2026)
ACL