# LexPath: A domain-oriented multi-path framework for legal article retrieval

Source: [LexPath: A domain-oriented multi-path framework for legal article retrieval](<https://www.sota2.com/research/paper/6a191dbadbd7150506f829c4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-30T05:00:11.986Z

Authors: Weixuan Liu, Qingfeng Zhuge, Xuyang Chen

Published: 2026-05-28T16:43:17.000Z

## 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 \\textsc{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. Then, the reranking module further refines the candidate ranking by incorporating the intent consistency score between queries and legal articles. We evaluate \\textsc{LexPath} on two publicly available benchmarks focusing on general-public queries and a self-constructed benchmark targeting domain-professional scenarios. Experimental results demonstrate that \\textsc{LexPath} consistently outperforms lexical, dense, hybrid, and adaptive retrieval-augmented generation (RAG) baselines. Ablation studies further verify the effectiveness of each component.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Legal Article Retrieval on STARD (test)](<https://www.sota2.com/research/sota/legal-article-retrieval-on-stard-test.md>): Legal Article Retrieval; STARD (test); Recall@1: 37.54.

- [Legal Article Retrieval on LexRAG (test)](<https://www.sota2.com/research/sota/legal-article-retrieval-on-lexrag-test.md>): Legal Article Retrieval; LexRAG (test); Recall@1: 16.86.

- [Legal Article Retrieval on StatuteRAG (test)](<https://www.sota2.com/research/sota/legal-article-retrieval-on-statuterag-test.md>): Legal Article Retrieval; StatuteRAG (test); Recall@1: 66.67.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.30205>)

[PDF](<https://arxiv.org/pdf/2605.30205.pdf>)