@inproceedings{carrer-etal-2026-evaluating,
title = "Evaluating {LLM}-based Text Simplification for {G}erman: Effects on Post-Editing Effort, Quality Ratings, and User Comprehension",
author = {Carrer, Luisa and
S{\"a}uberli, Andreas and
Kappus, Martin and
Fischer, Lukas and
Ebling, Sarah},
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.571/",
doi = "10.63317/3688akbpcnjn",
pages = "7192--7208",
abstract = "Automatic text simplification (ATS) seeks to automate the process of rewording within the same language to enhance readability and comprehension. Current evaluation practices for ATS systems predominantly rely on automatic metrics or assessments by experts and crowdworkers, often excluding the intended end users and other stakeholders, and thus limiting insights into the actual effectiveness of ATS models. In this study, we address this gap by conducting a multi-faceted, mixed-method evaluation of two LLM-based ATS systems for German (capito.ai and GPT-4o) and by involving end users, post-editors, and Easy Language experts. The findings highlight the effectiveness of the LLM-based ATS systems examined across several dimensions, including post-editing efficiency, expert quality assessments, and, in the case of GPT-4o-generated simplifications, user comprehension. Post-editing effort metrics, in particular, show an increase in productivity of around 30{\%} compared to full manual simplification. Moreover, the results reveal substantial differences in perception and understanding among participant groups. These outcomes clearly indicate that ATS for German has recently made considerable progress and, crucially, underscore the importance of incorporating multiple stakeholders into ATS evaluation to better align system performance with accessibility goals."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="carrer-etal-2026-evaluating">
<titleInfo>
<title>Evaluating LLM-based Text Simplification for German: Effects on Post-Editing Effort, Quality Ratings, and User Comprehension</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Carrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Säuberli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Kappus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lukas</namePart>
<namePart type="family">Fischer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Ebling</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic text simplification (ATS) seeks to automate the process of rewording within the same language to enhance readability and comprehension. Current evaluation practices for ATS systems predominantly rely on automatic metrics or assessments by experts and crowdworkers, often excluding the intended end users and other stakeholders, and thus limiting insights into the actual effectiveness of ATS models. In this study, we address this gap by conducting a multi-faceted, mixed-method evaluation of two LLM-based ATS systems for German (capito.ai and GPT-4o) and by involving end users, post-editors, and Easy Language experts. The findings highlight the effectiveness of the LLM-based ATS systems examined across several dimensions, including post-editing efficiency, expert quality assessments, and, in the case of GPT-4o-generated simplifications, user comprehension. Post-editing effort metrics, in particular, show an increase in productivity of around 30% compared to full manual simplification. Moreover, the results reveal substantial differences in perception and understanding among participant groups. These outcomes clearly indicate that ATS for German has recently made considerable progress and, crucially, underscore the importance of incorporating multiple stakeholders into ATS evaluation to better align system performance with accessibility goals.</abstract>
<identifier type="citekey">carrer-etal-2026-evaluating</identifier>
<identifier type="doi">10.63317/3688akbpcnjn</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.571/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7192</start>
<end>7208</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating LLM-based Text Simplification for German: Effects on Post-Editing Effort, Quality Ratings, and User Comprehension
%A Carrer, Luisa
%A Säuberli, Andreas
%A Kappus, Martin
%A Fischer, Lukas
%A Ebling, Sarah
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F carrer-etal-2026-evaluating
%X Automatic text simplification (ATS) seeks to automate the process of rewording within the same language to enhance readability and comprehension. Current evaluation practices for ATS systems predominantly rely on automatic metrics or assessments by experts and crowdworkers, often excluding the intended end users and other stakeholders, and thus limiting insights into the actual effectiveness of ATS models. In this study, we address this gap by conducting a multi-faceted, mixed-method evaluation of two LLM-based ATS systems for German (capito.ai and GPT-4o) and by involving end users, post-editors, and Easy Language experts. The findings highlight the effectiveness of the LLM-based ATS systems examined across several dimensions, including post-editing efficiency, expert quality assessments, and, in the case of GPT-4o-generated simplifications, user comprehension. Post-editing effort metrics, in particular, show an increase in productivity of around 30% compared to full manual simplification. Moreover, the results reveal substantial differences in perception and understanding among participant groups. These outcomes clearly indicate that ATS for German has recently made considerable progress and, crucially, underscore the importance of incorporating multiple stakeholders into ATS evaluation to better align system performance with accessibility goals.
%R 10.63317/3688akbpcnjn
%U https://aclanthology.org/2026.lrec-1.571/
%U https://doi.org/10.63317/3688akbpcnjn
%P 7192-7208
Markdown (Informal)
[Evaluating LLM-based Text Simplification for German: Effects on Post-Editing Effort, Quality Ratings, and User Comprehension](https://aclanthology.org/2026.lrec-1.571/) (Carrer et al., LREC 2026)
ACL