@inproceedings{sant-ana-etal-2026-structured,
title = "Structured Summaries for Retrieval-Augmented Generation in {P}ortuguese-Language Consumer Complaints",
author = "Sant'Ana, Rafael and
Garcia, Pedro and
Duarte, Luis A. and
Silva, Mariana O. and
Pereira, Adriano C. M. and
Pappa, Gisele L.",
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-1.84/",
pages = "847--857",
ISBN = "979-8-89176-387-6",
abstract = "Dense retrieval is a critical component of Retrieval-Augmented Generation (RAG) systems and is highly sensitive to document representations. In consumer complaint settings, raw interaction texts are often lengthy and noisy, which limits retrieval effectiveness. This paper investigates whether schema-guided structured summaries can improve dense retrieval in RAG. We compare embeddings derived from raw interaction texts and from LLM-generated structured summaries in a controlled evaluation on Portuguese-language consumer complaints. Summary-based retrieval achieves a Recall@1 of 0.527, compared to 0.001 when indexing raw interactions, and reaches Recall@10 of 0.610, demonstrating gains of more than two orders of magnitude. These results show that structured summaries enable more effective and reliable retrieval at low cutoffs, making them particularly suitable for RAG pipelines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sant-ana-etal-2026-structured">
<titleInfo>
<title>Structured Summaries for Retrieval-Augmented Generation in Portuguese-Language Consumer Complaints</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Sant’Ana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Duarte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="given">O</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adriano</namePart>
<namePart type="given">C</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Pereira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gisele</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Pappa</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>Dense retrieval is a critical component of Retrieval-Augmented Generation (RAG) systems and is highly sensitive to document representations. In consumer complaint settings, raw interaction texts are often lengthy and noisy, which limits retrieval effectiveness. This paper investigates whether schema-guided structured summaries can improve dense retrieval in RAG. We compare embeddings derived from raw interaction texts and from LLM-generated structured summaries in a controlled evaluation on Portuguese-language consumer complaints. Summary-based retrieval achieves a Recall@1 of 0.527, compared to 0.001 when indexing raw interactions, and reaches Recall@10 of 0.610, demonstrating gains of more than two orders of magnitude. These results show that structured summaries enable more effective and reliable retrieval at low cutoffs, making them particularly suitable for RAG pipelines.</abstract>
<identifier type="citekey">sant-ana-etal-2026-structured</identifier>
<location>
<url>https://aclanthology.org/2026.propor-1.84/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>847</start>
<end>857</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Structured Summaries for Retrieval-Augmented Generation in Portuguese-Language Consumer Complaints
%A Sant’Ana, Rafael
%A Garcia, Pedro
%A Duarte, Luis A.
%A Silva, Mariana O.
%A Pereira, Adriano C. M.
%A Pappa, Gisele L.
%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 sant-ana-etal-2026-structured
%X Dense retrieval is a critical component of Retrieval-Augmented Generation (RAG) systems and is highly sensitive to document representations. In consumer complaint settings, raw interaction texts are often lengthy and noisy, which limits retrieval effectiveness. This paper investigates whether schema-guided structured summaries can improve dense retrieval in RAG. We compare embeddings derived from raw interaction texts and from LLM-generated structured summaries in a controlled evaluation on Portuguese-language consumer complaints. Summary-based retrieval achieves a Recall@1 of 0.527, compared to 0.001 when indexing raw interactions, and reaches Recall@10 of 0.610, demonstrating gains of more than two orders of magnitude. These results show that structured summaries enable more effective and reliable retrieval at low cutoffs, making them particularly suitable for RAG pipelines.
%U https://aclanthology.org/2026.propor-1.84/
%P 847-857
Markdown (Informal)
[Structured Summaries for Retrieval-Augmented Generation in Portuguese-Language Consumer Complaints](https://aclanthology.org/2026.propor-1.84/) (Sant'Ana et al., PROPOR 2026)
ACL