@inproceedings{campos-etal-2026-nlp,
title = "{NLP}-based Page Classification for Efficient {LLM} Extraction from {B}razilian Public Tender Documents",
author = "Campos, Pedro and
Medeiros, Ivo de and
Ara{\'u}jo, Adailton 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-1.61/",
pages = "621--627",
ISBN = "979-8-89176-387-6",
abstract = "Extracting structured information from lengthy documents using Large Language Models (LLMs) is computationally expensive and prone to accuracy degradation as input size increases. We present a two-stage pipeline for extracting products from Brazilian tender documents (editais de licita{\c{c}}{\~a}o), combining NLP-based page classification with LLM extraction. We construct a novel dataset of 11,190 annotated pages from 350 documents across five product domains. Our experiments compare transformer-based classifiers (BERTimbau, DistilBERT) with classical machine learning approaches using engineered features. Results show that XGBoost with domain-specific features achieves 97.75{\%} F1-score, outperforming fine-tuned BERT models by over 4 percentage points. The complete pipeline reduces LLM input tokens by 64-88{\%} while maintaining extraction completeness, enabling cost-effective document processing at scale."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="campos-etal-2026-nlp">
<titleInfo>
<title>NLP-based Page Classification for Efficient LLM Extraction from Brazilian Public Tender Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Campos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivo</namePart>
<namePart type="given">de</namePart>
<namePart type="family">Medeiros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adailton</namePart>
<namePart type="given">de</namePart>
<namePart type="family">Araújo</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>Extracting structured information from lengthy documents using Large Language Models (LLMs) is computationally expensive and prone to accuracy degradation as input size increases. We present a two-stage pipeline for extracting products from Brazilian tender documents (editais de licitação), combining NLP-based page classification with LLM extraction. We construct a novel dataset of 11,190 annotated pages from 350 documents across five product domains. Our experiments compare transformer-based classifiers (BERTimbau, DistilBERT) with classical machine learning approaches using engineered features. Results show that XGBoost with domain-specific features achieves 97.75% F1-score, outperforming fine-tuned BERT models by over 4 percentage points. The complete pipeline reduces LLM input tokens by 64-88% while maintaining extraction completeness, enabling cost-effective document processing at scale.</abstract>
<identifier type="citekey">campos-etal-2026-nlp</identifier>
<location>
<url>https://aclanthology.org/2026.propor-1.61/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>621</start>
<end>627</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLP-based Page Classification for Efficient LLM Extraction from Brazilian Public Tender Documents
%A Campos, Pedro
%A Medeiros, Ivo de
%A Araújo, Adailton 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 campos-etal-2026-nlp
%X Extracting structured information from lengthy documents using Large Language Models (LLMs) is computationally expensive and prone to accuracy degradation as input size increases. We present a two-stage pipeline for extracting products from Brazilian tender documents (editais de licitação), combining NLP-based page classification with LLM extraction. We construct a novel dataset of 11,190 annotated pages from 350 documents across five product domains. Our experiments compare transformer-based classifiers (BERTimbau, DistilBERT) with classical machine learning approaches using engineered features. Results show that XGBoost with domain-specific features achieves 97.75% F1-score, outperforming fine-tuned BERT models by over 4 percentage points. The complete pipeline reduces LLM input tokens by 64-88% while maintaining extraction completeness, enabling cost-effective document processing at scale.
%U https://aclanthology.org/2026.propor-1.61/
%P 621-627
Markdown (Informal)
[NLP-based Page Classification for Efficient LLM Extraction from Brazilian Public Tender Documents](https://aclanthology.org/2026.propor-1.61/) (Campos et al., PROPOR 2026)
ACL