@inproceedings{maffeo-etal-2026-prompt,
title = "Prompt Engineering for Named Entity Extraction from {P}ortuguese Legal Documents",
author = "Maffeo, Giovanni and
Silva, Catarina and
Oliveira, Hugo Gon{\c{c}}alo",
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-1.116/",
pages = "1092--1097",
ISBN = "979-8-89176-387-6",
abstract = "The growing volume and complexity of legal texts highlight the need for automatic methods capable of extracting structured information from unstructured documents. Motivated by the limited availability and high cost of annotated legal data, this challenge is even more severe for the Portuguese language. This work investigates whether prompt engineering over Large Language Models (LLMs) can effectively support legal Named Entity Recognition (NER) in low-supervision and low-resource settings through In-Context Learning (ICL). Using the LeNER-Br corpus, we evaluate category-specific prompts, different chunking sizes, and prompt engineering strategies. Entity-level evaluation using Exact Match Micro F1 shows that prompt engineering has a stronger impact on performance than other strategies. The best results were obtained with larger models, the 4-bit quantised Qwen-2.5:32B and GPT-5.2, achieving scores of 57.9{\%} and 71.9{\%}, respectively, highlighting the potential of this approach as an alternative to traditional supervised NER pipelines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maffeo-etal-2026-prompt">
<titleInfo>
<title>Prompt Engineering for Named Entity Extraction from Portuguese Legal Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Maffeo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catarina</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="given">Gonçalo</namePart>
<namePart type="family">Oliveira</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 growing volume and complexity of legal texts highlight the need for automatic methods capable of extracting structured information from unstructured documents. Motivated by the limited availability and high cost of annotated legal data, this challenge is even more severe for the Portuguese language. This work investigates whether prompt engineering over Large Language Models (LLMs) can effectively support legal Named Entity Recognition (NER) in low-supervision and low-resource settings through In-Context Learning (ICL). Using the LeNER-Br corpus, we evaluate category-specific prompts, different chunking sizes, and prompt engineering strategies. Entity-level evaluation using Exact Match Micro F1 shows that prompt engineering has a stronger impact on performance than other strategies. The best results were obtained with larger models, the 4-bit quantised Qwen-2.5:32B and GPT-5.2, achieving scores of 57.9% and 71.9%, respectively, highlighting the potential of this approach as an alternative to traditional supervised NER pipelines.</abstract>
<identifier type="citekey">maffeo-etal-2026-prompt</identifier>
<location>
<url>https://aclanthology.org/2026.propor-1.116/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>1092</start>
<end>1097</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Prompt Engineering for Named Entity Extraction from Portuguese Legal Documents
%A Maffeo, Giovanni
%A Silva, Catarina
%A Oliveira, Hugo Gonçalo
%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 maffeo-etal-2026-prompt
%X The growing volume and complexity of legal texts highlight the need for automatic methods capable of extracting structured information from unstructured documents. Motivated by the limited availability and high cost of annotated legal data, this challenge is even more severe for the Portuguese language. This work investigates whether prompt engineering over Large Language Models (LLMs) can effectively support legal Named Entity Recognition (NER) in low-supervision and low-resource settings through In-Context Learning (ICL). Using the LeNER-Br corpus, we evaluate category-specific prompts, different chunking sizes, and prompt engineering strategies. Entity-level evaluation using Exact Match Micro F1 shows that prompt engineering has a stronger impact on performance than other strategies. The best results were obtained with larger models, the 4-bit quantised Qwen-2.5:32B and GPT-5.2, achieving scores of 57.9% and 71.9%, respectively, highlighting the potential of this approach as an alternative to traditional supervised NER pipelines.
%U https://aclanthology.org/2026.propor-1.116/
%P 1092-1097
Markdown (Informal)
[Prompt Engineering for Named Entity Extraction from Portuguese Legal Documents](https://aclanthology.org/2026.propor-1.116/) (Maffeo et al., PROPOR 2026)
ACL