@inproceedings{anschutz-etal-2025-german4all,
title = "{G}erman4{A}ll {--} A Dataset and Model for Readability-Controlled Paraphrasing in {G}erman",
author = {Ansch{\"u}tz, Miriam and
Pham, Thanh Mai and
Nasrallah, Eslam and
M{\"u}ller, Maximilian and
Craciun, Cristian-George and
Groh, Georg},
editor = "Flek, Lucie and
Narayan, Shashi and
Phương, L{\^e} Hồng and
Pei, Jiahuan",
booktitle = "Proceedings of the 18th International Natural Language Generation Conference",
month = oct,
year = "2025",
address = "Hanoi, Vietnam",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.inlg-main.24/",
pages = "390--407",
abstract = "The ability to paraphrase texts across different complexity levels is essential for creating accessible texts that can be tailored toward diverse reader groups. Thus, we introduce \textbf{German4All}, the first large-scale German dataset of aligned readability-controlled, paragraph-level paraphrases. It spans five readability levels and comprises over 25,000 samples. The dataset is automatically synthesized using GPT-4 and rigorously evaluated through both human and LLM-based judgments. Using German4All, we train an open-source, readability-controlled paraphrasing model that achieves state-of-the-art performance in German text simplification, enabling more nuanced and reader-specific adaptations. We open-source both the dataset and the model to encourage further research on multi-level paraphrasing."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="anschutz-etal-2025-german4all">
<titleInfo>
<title>German4All – A Dataset and Model for Readability-Controlled Paraphrasing in German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miriam</namePart>
<namePart type="family">Anschütz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanh</namePart>
<namePart type="given">Mai</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eslam</namePart>
<namePart type="family">Nasrallah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Müller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristian-George</namePart>
<namePart type="family">Craciun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Groh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Natural Language Generation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Flek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashi</namePart>
<namePart type="family">Narayan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lê</namePart>
<namePart type="given">Hồng</namePart>
<namePart type="family">Phương</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahuan</namePart>
<namePart type="family">Pei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hanoi, Vietnam</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The ability to paraphrase texts across different complexity levels is essential for creating accessible texts that can be tailored toward diverse reader groups. Thus, we introduce German4All, the first large-scale German dataset of aligned readability-controlled, paragraph-level paraphrases. It spans five readability levels and comprises over 25,000 samples. The dataset is automatically synthesized using GPT-4 and rigorously evaluated through both human and LLM-based judgments. Using German4All, we train an open-source, readability-controlled paraphrasing model that achieves state-of-the-art performance in German text simplification, enabling more nuanced and reader-specific adaptations. We open-source both the dataset and the model to encourage further research on multi-level paraphrasing.</abstract>
<identifier type="citekey">anschutz-etal-2025-german4all</identifier>
<location>
<url>https://aclanthology.org/2025.inlg-main.24/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>390</start>
<end>407</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T German4All – A Dataset and Model for Readability-Controlled Paraphrasing in German
%A Anschütz, Miriam
%A Pham, Thanh Mai
%A Nasrallah, Eslam
%A Müller, Maximilian
%A Craciun, Cristian-George
%A Groh, Georg
%Y Flek, Lucie
%Y Narayan, Shashi
%Y Phương, Lê Hồng
%Y Pei, Jiahuan
%S Proceedings of the 18th International Natural Language Generation Conference
%D 2025
%8 October
%I Association for Computational Linguistics
%C Hanoi, Vietnam
%F anschutz-etal-2025-german4all
%X The ability to paraphrase texts across different complexity levels is essential for creating accessible texts that can be tailored toward diverse reader groups. Thus, we introduce German4All, the first large-scale German dataset of aligned readability-controlled, paragraph-level paraphrases. It spans five readability levels and comprises over 25,000 samples. The dataset is automatically synthesized using GPT-4 and rigorously evaluated through both human and LLM-based judgments. Using German4All, we train an open-source, readability-controlled paraphrasing model that achieves state-of-the-art performance in German text simplification, enabling more nuanced and reader-specific adaptations. We open-source both the dataset and the model to encourage further research on multi-level paraphrasing.
%U https://aclanthology.org/2025.inlg-main.24/
%P 390-407
Markdown (Informal)
[German4All – A Dataset and Model for Readability-Controlled Paraphrasing in German](https://aclanthology.org/2025.inlg-main.24/) (Anschütz et al., INLG 2025)
ACL