@inproceedings{barros-etal-2026-superficiality,
title = "The Superficiality Bias: Community Votes and Answer Utility in {P}ortuguese Health Question Answering",
author = "Barros, Carlos Henrique Santos and
Sousa, Gustavo Figueredo Rodrigues de and
Sousa, Rog{\'e}rio Figueredo 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-1.113/",
pages = "1074--1078",
ISBN = "979-8-89176-387-6",
abstract = "Supervised models trained on community-labeled data have shown promise in Health Question Answering (HQA), but relying on ``likes'' as a proxy for clinical usefulness remains controversial. This work investigates the alignment between automated predictions and human perception in Portuguese HQA. Using a subset of the SaudeBR-QA corpus, we compare a Random Forest classifier against a controlled evaluation conducted by laypeople and healthcare professionals. Our results reveal a recurring divergence that we term \textbf{Superficiality Bias}: human evaluators frequently validate very brief answers, whereas the classifier often labels these cases as non-useful under its learned criteria. Rather than indicating that the model is inherently more clinically accurate, this pattern suggests a misalignment between community feedback and feature-driven utility judgments. We argue that crowd-based labels in medical domains should be treated cautiously and complemented with more rigorous annotation protocols."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barros-etal-2026-superficiality">
<titleInfo>
<title>The Superficiality Bias: Community Votes and Answer Utility in Portuguese Health Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="given">Henrique</namePart>
<namePart type="given">Santos</namePart>
<namePart type="family">Barros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gustavo</namePart>
<namePart type="given">Figueredo</namePart>
<namePart type="given">Rodrigues</namePart>
<namePart type="given">de</namePart>
<namePart type="family">Sousa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rogério</namePart>
<namePart type="given">Figueredo</namePart>
<namePart type="given">de</namePart>
<namePart type="family">Sousa</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>Supervised models trained on community-labeled data have shown promise in Health Question Answering (HQA), but relying on “likes” as a proxy for clinical usefulness remains controversial. This work investigates the alignment between automated predictions and human perception in Portuguese HQA. Using a subset of the SaudeBR-QA corpus, we compare a Random Forest classifier against a controlled evaluation conducted by laypeople and healthcare professionals. Our results reveal a recurring divergence that we term Superficiality Bias: human evaluators frequently validate very brief answers, whereas the classifier often labels these cases as non-useful under its learned criteria. Rather than indicating that the model is inherently more clinically accurate, this pattern suggests a misalignment between community feedback and feature-driven utility judgments. We argue that crowd-based labels in medical domains should be treated cautiously and complemented with more rigorous annotation protocols.</abstract>
<identifier type="citekey">barros-etal-2026-superficiality</identifier>
<location>
<url>https://aclanthology.org/2026.propor-1.113/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>1074</start>
<end>1078</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Superficiality Bias: Community Votes and Answer Utility in Portuguese Health Question Answering
%A Barros, Carlos Henrique Santos
%A Sousa, Gustavo Figueredo Rodrigues de
%A Sousa, Rogério Figueredo 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 barros-etal-2026-superficiality
%X Supervised models trained on community-labeled data have shown promise in Health Question Answering (HQA), but relying on “likes” as a proxy for clinical usefulness remains controversial. This work investigates the alignment between automated predictions and human perception in Portuguese HQA. Using a subset of the SaudeBR-QA corpus, we compare a Random Forest classifier against a controlled evaluation conducted by laypeople and healthcare professionals. Our results reveal a recurring divergence that we term Superficiality Bias: human evaluators frequently validate very brief answers, whereas the classifier often labels these cases as non-useful under its learned criteria. Rather than indicating that the model is inherently more clinically accurate, this pattern suggests a misalignment between community feedback and feature-driven utility judgments. We argue that crowd-based labels in medical domains should be treated cautiously and complemented with more rigorous annotation protocols.
%U https://aclanthology.org/2026.propor-1.113/
%P 1074-1078
Markdown (Informal)
[The Superficiality Bias: Community Votes and Answer Utility in Portuguese Health Question Answering](https://aclanthology.org/2026.propor-1.113/) (Barros et al., PROPOR 2026)
ACL