<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ledoyen-etal-2025-facilitating">
    <titleInfo>
        <title>Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">François</namePart>
        <namePart type="family">Ledoyen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gaël</namePart>
        <namePart type="family">Dias</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jeremie</namePart>
        <namePart type="family">Pantin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexis</namePart>
        <namePart type="family">Lechervy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fabrice</namePart>
        <namePart type="family">Maurel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Youssef</namePart>
        <namePart type="family">Chahir</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-332-6</identifier>
    </relatedItem>
    <abstract>Simplifying complex texts is essential to ensure equitable access to information, particularly for individuals with cognitive impairments. The Easy-to-Read (ETR) initiative provides a framework to make content more accessible for these individuals. However, manually creating such texts remains time-consuming and resource-intensive. In this work, we investigate the potential of large language models (LLMs) to automate the generation of ETR content. To address the scarcity of aligned corpora and the specific constraints of ETR, we propose a multi-task learning (MTL) approach that trains models jointly on text summarization, text simplification, and ETR generation. We explore two complementary strategies: multi-task retrieval-augmented generation (RAG) for in-context learning (ICL), and MTL-LoRA for parameter-efficient fine-tuning (PEFT). Our experiments with Mistral-7B and LLaMA-3-8B, conducted on ETR-fr, a new high-quality dataset, show that MTL-LoRA consistently outperforms all other strategies in in-domain settings, while the MTL-RAG-based approach achieves better generalization in out-of-domain scenarios. Our code is publicly available at https://github.com/FrLdy/ETR-PEFT-Composition.</abstract>
    <identifier type="citekey">ledoyen-etal-2025-facilitating</identifier>
    <identifier type="doi">10.18653/v1/2025.emnlp-main.596</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.596/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>11771</start>
            <end>11797</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation
%A Ledoyen, François
%A Dias, Gaël
%A Pantin, Jeremie
%A Lechervy, Alexis
%A Maurel, Fabrice
%A Chahir, Youssef
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F ledoyen-etal-2025-facilitating
%X Simplifying complex texts is essential to ensure equitable access to information, particularly for individuals with cognitive impairments. The Easy-to-Read (ETR) initiative provides a framework to make content more accessible for these individuals. However, manually creating such texts remains time-consuming and resource-intensive. In this work, we investigate the potential of large language models (LLMs) to automate the generation of ETR content. To address the scarcity of aligned corpora and the specific constraints of ETR, we propose a multi-task learning (MTL) approach that trains models jointly on text summarization, text simplification, and ETR generation. We explore two complementary strategies: multi-task retrieval-augmented generation (RAG) for in-context learning (ICL), and MTL-LoRA for parameter-efficient fine-tuning (PEFT). Our experiments with Mistral-7B and LLaMA-3-8B, conducted on ETR-fr, a new high-quality dataset, show that MTL-LoRA consistently outperforms all other strategies in in-domain settings, while the MTL-RAG-based approach achieves better generalization in out-of-domain scenarios. Our code is publicly available at https://github.com/FrLdy/ETR-PEFT-Composition.
%R 10.18653/v1/2025.emnlp-main.596
%U https://aclanthology.org/2025.emnlp-main.596/
%U https://doi.org/10.18653/v1/2025.emnlp-main.596
%P 11771-11797

Markdown (Informal)

[Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation](https://aclanthology.org/2025.emnlp-main.596/) (Ledoyen et al., EMNLP 2025)

• Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation (Ledoyen et al., EMNLP 2025)

ACL

• François Ledoyen, Gaël Dias, Jeremie Pantin, Alexis Lechervy, Fabrice Maurel, and Youssef Chahir. 2025. Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 11771–11797, Suzhou, China. Association for Computational Linguistics.