@inproceedings{pereira-etal-2026-legal,
title = "Legal Nugget Extraction for Granular Retrieval over Long Jurisprudential Texts",
author = "Pereira, Lucas and
Brito, Erick and
Lotufo, Roberto and
Pereira, Jayr",
editor = "Barbosa, Bryan Khelven da Silva and
Paes, Aline and
Felippo, Ariani Di",
booktitle = "Proceedings of the 17th {B}razilian Symposium in Information and Human Language Technology",
month = oct,
year = "2026",
address = "Cuiab{\'a}, Mato Grosso, Brazil",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.stil-1.26/",
doi = "10.5753/stil.2026.26588",
pages = "305--316",
abstract = "Legal retrieval over jurisprudential collections is challenging because court decisions are long, heterogeneous documents whose relevant legal thesis may occupy only a small portion of the text. This paper asks whether legal nuggets, defined as short and self-contained legal theses extracted from source documents, can improve dense retrieval over Brazilian legal collections. We propose a pipeline that extracts nuggets from each document, indexes them with embeddings, retrieves nugget-level evidence, and aggregates the retrieved nuggets back to document-level rankings. We evaluate this approach on four Portuguese legal retrieval benchmarks from the JUA ecosystem, reporting NDCG@10, MAP@10, and MRR@10. Nugget retrieval substantially improves the two jurisprudential datasets: on JUA-Juris, NDCG@10 increases from 0.10265 to 0.20461, and on JurisTCU from 0.20898 to 0.32696. However, it underperforms full-document retrieval on NormasTCU and BR-TaxQA, and an embedding-model ablation shows that strong domain-adapted retrievers can remain better in the full-document setting. The results demonstrate that legal nuggets can be useful for jurisprudence search, especially when queries are formulated as legal theses, but they may not transfer equally well to other legal retrieval scenarios."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pereira-etal-2026-legal">
<titleInfo>
<title>Legal Nugget Extraction for Granular Retrieval over Long Jurisprudential Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Pereira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erick</namePart>
<namePart type="family">Brito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Lotufo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jayr</namePart>
<namePart type="family">Pereira</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 17th Brazilian Symposium in Information and Human Language Technology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="given">Khelven</namePart>
<namePart type="given">da</namePart>
<namePart type="given">Silva</namePart>
<namePart type="family">Barbosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Paes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ariani</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Felippo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Cuiabá, Mato Grosso, Brazil</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Legal retrieval over jurisprudential collections is challenging because court decisions are long, heterogeneous documents whose relevant legal thesis may occupy only a small portion of the text. This paper asks whether legal nuggets, defined as short and self-contained legal theses extracted from source documents, can improve dense retrieval over Brazilian legal collections. We propose a pipeline that extracts nuggets from each document, indexes them with embeddings, retrieves nugget-level evidence, and aggregates the retrieved nuggets back to document-level rankings. We evaluate this approach on four Portuguese legal retrieval benchmarks from the JUA ecosystem, reporting NDCG@10, MAP@10, and MRR@10. Nugget retrieval substantially improves the two jurisprudential datasets: on JUA-Juris, NDCG@10 increases from 0.10265 to 0.20461, and on JurisTCU from 0.20898 to 0.32696. However, it underperforms full-document retrieval on NormasTCU and BR-TaxQA, and an embedding-model ablation shows that strong domain-adapted retrievers can remain better in the full-document setting. The results demonstrate that legal nuggets can be useful for jurisprudence search, especially when queries are formulated as legal theses, but they may not transfer equally well to other legal retrieval scenarios.</abstract>
<identifier type="citekey">pereira-etal-2026-legal</identifier>
<identifier type="doi">10.5753/stil.2026.26588</identifier>
<location>
<url>https://aclanthology.org/2026.stil-1.26/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>305</start>
<end>316</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Legal Nugget Extraction for Granular Retrieval over Long Jurisprudential Texts
%A Pereira, Lucas
%A Brito, Erick
%A Lotufo, Roberto
%A Pereira, Jayr
%Y Barbosa, Bryan Khelven da Silva
%Y Paes, Aline
%Y Felippo, Ariani Di
%S Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology
%D 2026
%8 October
%I Association for Computational Linguistics
%C Cuiabá, Mato Grosso, Brazil
%F pereira-etal-2026-legal
%X Legal retrieval over jurisprudential collections is challenging because court decisions are long, heterogeneous documents whose relevant legal thesis may occupy only a small portion of the text. This paper asks whether legal nuggets, defined as short and self-contained legal theses extracted from source documents, can improve dense retrieval over Brazilian legal collections. We propose a pipeline that extracts nuggets from each document, indexes them with embeddings, retrieves nugget-level evidence, and aggregates the retrieved nuggets back to document-level rankings. We evaluate this approach on four Portuguese legal retrieval benchmarks from the JUA ecosystem, reporting NDCG@10, MAP@10, and MRR@10. Nugget retrieval substantially improves the two jurisprudential datasets: on JUA-Juris, NDCG@10 increases from 0.10265 to 0.20461, and on JurisTCU from 0.20898 to 0.32696. However, it underperforms full-document retrieval on NormasTCU and BR-TaxQA, and an embedding-model ablation shows that strong domain-adapted retrievers can remain better in the full-document setting. The results demonstrate that legal nuggets can be useful for jurisprudence search, especially when queries are formulated as legal theses, but they may not transfer equally well to other legal retrieval scenarios.
%R 10.5753/stil.2026.26588
%U https://aclanthology.org/2026.stil-1.26/
%U https://doi.org/10.5753/stil.2026.26588
%P 305-316
Markdown (Informal)
[Legal Nugget Extraction for Granular Retrieval over Long Jurisprudential Texts](https://aclanthology.org/2026.stil-1.26/) (Pereira et al., STIL 2026)
ACL