@inproceedings{garcia-etal-2026-retrieval,
title = "Retrieval-Augmented Generation for Clinical Question Answering in {P}ortuguese Drug Leaflets: Benefits and Limitations",
author = "Garcia, Gabriel Lino and
Paiola, Pedro Henrique and
Correia, Jo{\~a}o Vitor Mariano and
Rodrigues, Douglas and
Papa, Jo{\~a}o Paulo",
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. 2",
month = apr,
year = "2026",
address = "Salvador, Brazil",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.propor-2.18/",
pages = "112--120",
ISBN = "979-8-89176-387-6",
abstract = "Retrieval-Augmented Generation (RAG) is proposed to reduce hallucination and improve grounding in clinical language models, yet its effectiveness across different levels of clinical reasoning remains unclear. We conducted a controlled evaluation of medication-related question answering in Portuguese using over 7,000 Brazilian regulatory drug leaflets and a complementary clinical benchmark derived from national medical licensing examinations (Revalida and Fuvest). Retrieval substantially improved factual recall and clinical coherence in medication-specific queries, increasing F1 from 0.276 to 0.412. However, naive retrieval did not consistently improve complex clinical reasoning and sometimes reduced accuracy compared to a parametric-only baseline. We identify retrieval-induced anchoring bias, where partially relevant evidence shifts model decisions toward clinically incorrect conclusions. Critique-based and adaptive retrieval mitigated this effect and achieved the highest clinical benchmark accuracy (54.25{\%}). Clinically grounded evaluation dimensions revealed safety-relevant differences beyond traditional NLP metrics. These results show that retrieval augmentation is effective in regulatory settings but requires adaptive control for higher-level clinical reasoning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-etal-2026-retrieval">
<titleInfo>
<title>Retrieval-Augmented Generation for Clinical Question Answering in Portuguese Drug Leaflets: Benefits and Limitations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="given">Lino</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="given">Henrique</namePart>
<namePart type="family">Paiola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="given">Vitor</namePart>
<namePart type="given">Mariano</namePart>
<namePart type="family">Correia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Douglas</namePart>
<namePart type="family">Rodrigues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="given">Paulo</namePart>
<namePart type="family">Papa</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. 2</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>Retrieval-Augmented Generation (RAG) is proposed to reduce hallucination and improve grounding in clinical language models, yet its effectiveness across different levels of clinical reasoning remains unclear. We conducted a controlled evaluation of medication-related question answering in Portuguese using over 7,000 Brazilian regulatory drug leaflets and a complementary clinical benchmark derived from national medical licensing examinations (Revalida and Fuvest). Retrieval substantially improved factual recall and clinical coherence in medication-specific queries, increasing F1 from 0.276 to 0.412. However, naive retrieval did not consistently improve complex clinical reasoning and sometimes reduced accuracy compared to a parametric-only baseline. We identify retrieval-induced anchoring bias, where partially relevant evidence shifts model decisions toward clinically incorrect conclusions. Critique-based and adaptive retrieval mitigated this effect and achieved the highest clinical benchmark accuracy (54.25%). Clinically grounded evaluation dimensions revealed safety-relevant differences beyond traditional NLP metrics. These results show that retrieval augmentation is effective in regulatory settings but requires adaptive control for higher-level clinical reasoning.</abstract>
<identifier type="citekey">garcia-etal-2026-retrieval</identifier>
<location>
<url>https://aclanthology.org/2026.propor-2.18/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>112</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retrieval-Augmented Generation for Clinical Question Answering in Portuguese Drug Leaflets: Benefits and Limitations
%A Garcia, Gabriel Lino
%A Paiola, Pedro Henrique
%A Correia, João Vitor Mariano
%A Rodrigues, Douglas
%A Papa, João Paulo
%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. 2
%D 2026
%8 April
%I Association for Computational Linguistics
%C Salvador, Brazil
%@ 979-8-89176-387-6
%F garcia-etal-2026-retrieval
%X Retrieval-Augmented Generation (RAG) is proposed to reduce hallucination and improve grounding in clinical language models, yet its effectiveness across different levels of clinical reasoning remains unclear. We conducted a controlled evaluation of medication-related question answering in Portuguese using over 7,000 Brazilian regulatory drug leaflets and a complementary clinical benchmark derived from national medical licensing examinations (Revalida and Fuvest). Retrieval substantially improved factual recall and clinical coherence in medication-specific queries, increasing F1 from 0.276 to 0.412. However, naive retrieval did not consistently improve complex clinical reasoning and sometimes reduced accuracy compared to a parametric-only baseline. We identify retrieval-induced anchoring bias, where partially relevant evidence shifts model decisions toward clinically incorrect conclusions. Critique-based and adaptive retrieval mitigated this effect and achieved the highest clinical benchmark accuracy (54.25%). Clinically grounded evaluation dimensions revealed safety-relevant differences beyond traditional NLP metrics. These results show that retrieval augmentation is effective in regulatory settings but requires adaptive control for higher-level clinical reasoning.
%U https://aclanthology.org/2026.propor-2.18/
%P 112-120
Markdown (Informal)
[Retrieval-Augmented Generation for Clinical Question Answering in Portuguese Drug Leaflets: Benefits and Limitations](https://aclanthology.org/2026.propor-2.18/) (Garcia et al., PROPOR 2026)
ACL