@inproceedings{esashika-etal-2026-discovery,
title = "Discovery of Legal Patterns in Civil Petitions via {LLM}-Based Fact Extraction and Density Clustering",
author = "Esashika, Rhedson and
Figueiredo, Carlos M. S. and
Melo, Tiago de",
editor = "Souza, Marlo and
de-Dios-Flores, Iria and
Santos, Diana and
Freitas, Larissa and
Souza, Jackson Wilke da Cruz and
Ribeiro, Eug{\'e}nio",
booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 1",
month = apr,
year = "2026",
address = "Salvador, Brazil",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.propor-1.41/",
pages = "416--424",
ISBN = "979-8-89176-387-6",
abstract = "The analysis of unstructured civil petitions is often hindered by procedural noise and verbose argumentation. To address this, we propose a pipeline composed of LLM-based fact extraction followed by legal-domain embeddings of texts for unsupervised density clustering. We employ Large Language Models to isolate factual narratives from raw texts, which are then encoded using domain-specific representations (Legal-BERT) and grouped via UMAP dimensionality reduction and the HDBSCAN algorithm. Comparative experiments on a Brazilian judicial corpus reveal that clustering based solely on extracted yields significantly more cohesive and semantically well-defined groups than, which suffer from fragmentation due to content variability. Results indicate that the proposed method is a promising approach for thematic organization, procedural triage support, and large-scale discovery of legal patterns."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="esashika-etal-2026-discovery">
<titleInfo>
<title>Discovery of Legal Patterns in Civil Petitions via LLM-Based Fact Extraction and Density Clustering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rhedson</namePart>
<namePart type="family">Esashika</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="given">M</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Figueiredo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiago</namePart>
<namePart type="given">de</namePart>
<namePart type="family">Melo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marlo</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iria</namePart>
<namePart type="family">de-Dios-Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larissa</namePart>
<namePart type="family">Freitas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jackson</namePart>
<namePart type="given">Wilke</namePart>
<namePart type="given">da</namePart>
<namePart type="given">Cruz</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugénio</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Salvador, Brazil</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-387-6</identifier>
</relatedItem>
<abstract>The analysis of unstructured civil petitions is often hindered by procedural noise and verbose argumentation. To address this, we propose a pipeline composed of LLM-based fact extraction followed by legal-domain embeddings of texts for unsupervised density clustering. We employ Large Language Models to isolate factual narratives from raw texts, which are then encoded using domain-specific representations (Legal-BERT) and grouped via UMAP dimensionality reduction and the HDBSCAN algorithm. Comparative experiments on a Brazilian judicial corpus reveal that clustering based solely on extracted yields significantly more cohesive and semantically well-defined groups than, which suffer from fragmentation due to content variability. Results indicate that the proposed method is a promising approach for thematic organization, procedural triage support, and large-scale discovery of legal patterns.</abstract>
<identifier type="citekey">esashika-etal-2026-discovery</identifier>
<location>
<url>https://aclanthology.org/2026.propor-1.41/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>416</start>
<end>424</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Discovery of Legal Patterns in Civil Petitions via LLM-Based Fact Extraction and Density Clustering
%A Esashika, Rhedson
%A Figueiredo, Carlos M. S.
%A Melo, Tiago de
%Y Souza, Marlo
%Y de-Dios-Flores, Iria
%Y Santos, Diana
%Y Freitas, Larissa
%Y Souza, Jackson Wilke da Cruz
%Y Ribeiro, Eugénio
%S Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1
%D 2026
%8 April
%I Association for Computational Linguistics
%C Salvador, Brazil
%@ 979-8-89176-387-6
%F esashika-etal-2026-discovery
%X The analysis of unstructured civil petitions is often hindered by procedural noise and verbose argumentation. To address this, we propose a pipeline composed of LLM-based fact extraction followed by legal-domain embeddings of texts for unsupervised density clustering. We employ Large Language Models to isolate factual narratives from raw texts, which are then encoded using domain-specific representations (Legal-BERT) and grouped via UMAP dimensionality reduction and the HDBSCAN algorithm. Comparative experiments on a Brazilian judicial corpus reveal that clustering based solely on extracted yields significantly more cohesive and semantically well-defined groups than, which suffer from fragmentation due to content variability. Results indicate that the proposed method is a promising approach for thematic organization, procedural triage support, and large-scale discovery of legal patterns.
%U https://aclanthology.org/2026.propor-1.41/
%P 416-424
Markdown (Informal)
[Discovery of Legal Patterns in Civil Petitions via LLM-Based Fact Extraction and Density Clustering](https://aclanthology.org/2026.propor-1.41/) (Esashika et al., PROPOR 2026)
ACL