@inproceedings{ducel-etal-2025-women,
title = "``Women do not have heart attacks!'' Gender Biases in Automatically Generated Clinical Cases in {F}rench",
author = {Ducel, Fanny and
Hiebel, Nicolas and
Ferret, Olivier and
Fort, Kar{\"e}n and
N{\'e}v{\'e}ol, Aur{\'e}lie},
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.398/",
doi = "10.18653/v1/2025.findings-naacl.398",
pages = "7145--7159",
ISBN = "979-8-89176-195-7",
abstract = "Healthcare professionals are increasingly including Language Models (LMs) in clinical practice. However, LMs have been shown to exhibit and amplify stereotypical biases that can cause life-threatening harm in a medical context. This study aims to evaluate gender biases in automatically generated clinical cases in French, on ten disorders. Using seven LMs fine-tuned for clinical case generation and an automatic linguistic gender detection tool, we measure the associations between disorders and gender. We unveil that LMs over-generate cases describing male patients, creating synthetic corpora that are not consistent with documented prevalence for these disorders. For instance, when prompts do not specify a gender, LMs generate eight times more clinical cases describing male (vs. female patients) for heart attack. We discuss the ideal synthetic clinical case corpus and establish that explicitly mentioning demographic information in generation instructions appears to be the fairest strategy. In conclusion, we argue that the presence of gender biases in synthetic text raises concerns about LM-induced harm, especially for women and transgender people."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ducel-etal-2025-women">
<titleInfo>
<title>“Women do not have heart attacks!” Gender Biases in Automatically Generated Clinical Cases in French</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fanny</namePart>
<namePart type="family">Ducel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Hiebel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Ferret</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karën</namePart>
<namePart type="family">Fort</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurélie</namePart>
<namePart type="family">Névéol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Healthcare professionals are increasingly including Language Models (LMs) in clinical practice. However, LMs have been shown to exhibit and amplify stereotypical biases that can cause life-threatening harm in a medical context. This study aims to evaluate gender biases in automatically generated clinical cases in French, on ten disorders. Using seven LMs fine-tuned for clinical case generation and an automatic linguistic gender detection tool, we measure the associations between disorders and gender. We unveil that LMs over-generate cases describing male patients, creating synthetic corpora that are not consistent with documented prevalence for these disorders. For instance, when prompts do not specify a gender, LMs generate eight times more clinical cases describing male (vs. female patients) for heart attack. We discuss the ideal synthetic clinical case corpus and establish that explicitly mentioning demographic information in generation instructions appears to be the fairest strategy. In conclusion, we argue that the presence of gender biases in synthetic text raises concerns about LM-induced harm, especially for women and transgender people.</abstract>
<identifier type="citekey">ducel-etal-2025-women</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.398</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.398/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>7145</start>
<end>7159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T “Women do not have heart attacks!” Gender Biases in Automatically Generated Clinical Cases in French
%A Ducel, Fanny
%A Hiebel, Nicolas
%A Ferret, Olivier
%A Fort, Karën
%A Névéol, Aurélie
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F ducel-etal-2025-women
%X Healthcare professionals are increasingly including Language Models (LMs) in clinical practice. However, LMs have been shown to exhibit and amplify stereotypical biases that can cause life-threatening harm in a medical context. This study aims to evaluate gender biases in automatically generated clinical cases in French, on ten disorders. Using seven LMs fine-tuned for clinical case generation and an automatic linguistic gender detection tool, we measure the associations between disorders and gender. We unveil that LMs over-generate cases describing male patients, creating synthetic corpora that are not consistent with documented prevalence for these disorders. For instance, when prompts do not specify a gender, LMs generate eight times more clinical cases describing male (vs. female patients) for heart attack. We discuss the ideal synthetic clinical case corpus and establish that explicitly mentioning demographic information in generation instructions appears to be the fairest strategy. In conclusion, we argue that the presence of gender biases in synthetic text raises concerns about LM-induced harm, especially for women and transgender people.
%R 10.18653/v1/2025.findings-naacl.398
%U https://aclanthology.org/2025.findings-naacl.398/
%U https://doi.org/10.18653/v1/2025.findings-naacl.398
%P 7145-7159
Markdown (Informal)
[“Women do not have heart attacks!” Gender Biases in Automatically Generated Clinical Cases in French](https://aclanthology.org/2025.findings-naacl.398/) (Ducel et al., Findings 2025)
ACL