# Unlocking Legal Knowledge with Multi-Layered Embedding-Based Retrieval

arXiv: https://arxiv.org/abs/2411.07739 · HTML: https://mlsanity.com/paper/2411.07739/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 8 references that are in the map.
- First posted on arXiv 12 Nov 2024.

## Builds on (most cited first, 1 of 1)

- [A Survey on Retrieval-Augmented Text Generation for Large Language Models](https://mlsanity.com/paper/2404.10981/) (2024)

## Built on by (most cited first, 4 of 4)

- [Improving RAG Retrieval via Propositional Content Extraction: a Speech Act Theory Approach](https://mlsanity.com/paper/2503.10654/) (2025)
- [Poly-Vector Retrieval: Reference and Content Embeddings for Legal Documents](https://mlsanity.com/paper/2504.10508/) (2025)
- [Are manual annotations necessary for statutory interpretations retrieval?](https://mlsanity.com/paper/2506.13965/) (2025)
- [Beyond Probabilistic Similarity: Structural, Temporal, and Causal Limitations of Retrieval-Augmented Generation in the Legal Domain](https://mlsanity.com/paper/2606.09724/) (2026)

## Abstract (arXiv)

This work addresses the challenge of capturing the complexities of legal knowledge by proposing a multi-layered embedding-based retrieval method for legal and legislative texts. Creating embeddings not only for individual articles but also for their components (paragraphs, clauses) and structural groupings (books, titles, chapters, etc), we seek to capture the subtleties of legal information through the use of dense vectors of embeddings, representing it at varying levels of granularity. Our method meets various information needs by allowing the Retrieval Augmented Generation system to provide accurate responses, whether for specific segments or entire sections, tailored to the user's query. We explore the concepts of aboutness, semantic chunking, and inherent hierarchy within legal texts, arguing that this method enhances the legal information retrieval. Despite the focus being on Brazil's legislative methods and the Brazilian Constitution, which follow a civil law tradition, our findings should in principle be applicable across different legal systems, including those adhering to common law traditions. Furthermore, the principles of the proposed method extend beyond the legal domain, offering valuable insights for organizing and retrieving information in any field characterized by information encoded in hierarchical text.