@inproceedings{cardon-dogruoz-2026-automatic,
title = "Automatic Text Simplification for {F}rench Medical Documents with {LLM}s: The Role of Target Audience and Genre",
author = {Cardon, R{\'e}mi and
Do{\u{g}}ru{\"o}z, A. Seza},
editor = "Shardlow, Matthew and
Fran{\c{c}}ois, Thomas and
Amaro, Raquel and
Baptista, Jorge and
Cardon, R{\'e}mi and
Ribeiro, Eug{\'e}nio and
Saggion, Horacio and
Stodden, Regina and
Todirascu, Amalia and
Wilkens, Rodrigo",
booktitle = "Proceedings of the Joint Workshop on Readability and Text Simplification ({READI}x{TSAR}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.readi-1.13/",
doi = "10.63317/32b2v7b42kyb",
pages = "164--180",
abstract = "Medical information is hard for non-specialists to understand, despite its importance for treatment success. Automatic text simplification (ATS) rewrites complex documents into simpler versions, with effectiveness measured through ATS evaluation metrics and readability metrics. A key challenge in ATS is calibrating simplification to match the reading abilities of specific target audiences, as different populations have different comprehension needs. Since socio-demographic factors such as education level and health literacy are known to correlate with reading abilities, we hypothesize that large language models (LLMs) may be able to adjust their simplification strategies when provided with descriptions of target audiences. In this study, we investigate how LLMs simplify French medical documents when prompted with socio-demographic characteristics of target patients. We compare this approach with prompts based on language proficiency levels (CEFR) to determine whether LLMs respond differently to explicit proficiency levels versus implicit audience descriptions. Our experiments with five LLMs on three types of French medical documents show that CEFR prompts produce greater readability variation (particularly for Llama-3.1-8B), while socio-demographic factors yield more homogeneous outputs. Text genre also considerably impacts LLM outputs for ATS."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cardon-dogruoz-2026-automatic">
<titleInfo>
<title>Automatic Text Simplification for French Medical Documents with LLMs: The Role of Target Audience and Genre</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rémi</namePart>
<namePart type="family">Cardon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop on Readability and Text Simplification (READIxTSAR) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">François</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Amaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Baptista</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rémi</namePart>
<namePart type="family">Cardon</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>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Stodden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amalia</namePart>
<namePart type="family">Todirascu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="family">Wilkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Medical information is hard for non-specialists to understand, despite its importance for treatment success. Automatic text simplification (ATS) rewrites complex documents into simpler versions, with effectiveness measured through ATS evaluation metrics and readability metrics. A key challenge in ATS is calibrating simplification to match the reading abilities of specific target audiences, as different populations have different comprehension needs. Since socio-demographic factors such as education level and health literacy are known to correlate with reading abilities, we hypothesize that large language models (LLMs) may be able to adjust their simplification strategies when provided with descriptions of target audiences. In this study, we investigate how LLMs simplify French medical documents when prompted with socio-demographic characteristics of target patients. We compare this approach with prompts based on language proficiency levels (CEFR) to determine whether LLMs respond differently to explicit proficiency levels versus implicit audience descriptions. Our experiments with five LLMs on three types of French medical documents show that CEFR prompts produce greater readability variation (particularly for Llama-3.1-8B), while socio-demographic factors yield more homogeneous outputs. Text genre also considerably impacts LLM outputs for ATS.</abstract>
<identifier type="citekey">cardon-dogruoz-2026-automatic</identifier>
<identifier type="doi">10.63317/32b2v7b42kyb</identifier>
<location>
<url>https://aclanthology.org/2026.readi-1.13/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>164</start>
<end>180</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Text Simplification for French Medical Documents with LLMs: The Role of Target Audience and Genre
%A Cardon, Rémi
%A Doğruöz, A. Seza
%Y Shardlow, Matthew
%Y François, Thomas
%Y Amaro, Raquel
%Y Baptista, Jorge
%Y Cardon, Rémi
%Y Ribeiro, Eugénio
%Y Saggion, Horacio
%Y Stodden, Regina
%Y Todirascu, Amalia
%Y Wilkens, Rodrigo
%S Proceedings of the Joint Workshop on Readability and Text Simplification (READIxTSAR) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F cardon-dogruoz-2026-automatic
%X Medical information is hard for non-specialists to understand, despite its importance for treatment success. Automatic text simplification (ATS) rewrites complex documents into simpler versions, with effectiveness measured through ATS evaluation metrics and readability metrics. A key challenge in ATS is calibrating simplification to match the reading abilities of specific target audiences, as different populations have different comprehension needs. Since socio-demographic factors such as education level and health literacy are known to correlate with reading abilities, we hypothesize that large language models (LLMs) may be able to adjust their simplification strategies when provided with descriptions of target audiences. In this study, we investigate how LLMs simplify French medical documents when prompted with socio-demographic characteristics of target patients. We compare this approach with prompts based on language proficiency levels (CEFR) to determine whether LLMs respond differently to explicit proficiency levels versus implicit audience descriptions. Our experiments with five LLMs on three types of French medical documents show that CEFR prompts produce greater readability variation (particularly for Llama-3.1-8B), while socio-demographic factors yield more homogeneous outputs. Text genre also considerably impacts LLM outputs for ATS.
%R 10.63317/32b2v7b42kyb
%U https://aclanthology.org/2026.readi-1.13/
%U https://doi.org/10.63317/32b2v7b42kyb
%P 164-180
Markdown (Informal)
[Automatic Text Simplification for French Medical Documents with LLMs: The Role of Target Audience and Genre](https://aclanthology.org/2026.readi-1.13/) (Cardon & Doğruöz, READI-TSAR 2026)
ACL