@inproceedings{alva-manchego-etal-2025-findings,
title = "Findings of the {TSAR} 2025 Shared Task on Readability-Controlled Text Simplification",
author = "Alva-Manchego, Fernando and
Stodden, Regina and
Imperial, Joseph Marvin and
Barayan, Abdullah and
North, Kai and
Tayyar Madabushi, Harish",
editor = "Shardlow, Matthew and
Alva-Manchego, Fernando and
North, Kai and
Stodden, Regina and
Saggion, Horacio and
Khallaf, Nouran and
Hayakawa, Akio",
booktitle = "Proceedings of the Fourth Workshop on Text Simplification, Accessibility and Readability (TSAR 2025)",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.tsar-1.8/",
pages = "116--130",
ISBN = "979-8-89176-176-6",
abstract = "This paper presents the findings of the first Shared Task on Readability-Controlled Text Simplification at TSAR 2025. The task required systems to simplify English texts to specific target readability levels of the Common European Framework of Reference for Languages (CEFR). We received 48 submissions from 20 participating teams, with approaches predominantly based on large language models (LLMs), which included iterative refinement, multi-agent setups, and LLM-as-a-judge pipelines. For this shared task, we developed a new dataset of pedagogical texts and evaluated submissions using a weighted combination of semantic similarity and CEFR-level accuracy. The results of the participating teams demonstrate that while LLMs can perform substantially well on this task, dependable and controlled simplification often requires complex, multi-iterative processes. Our findings also suggest that the capabilities of current systems are beginning to saturate existing automatic evaluation metrics, underscoring the need for reevaluation and practicality."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alva-manchego-etal-2025-findings">
<titleInfo>
<title>Findings of the TSAR 2025 Shared Task on Readability-Controlled Text Simplification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Alva-Manchego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Stodden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="given">Marvin</namePart>
<namePart type="family">Imperial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="family">Barayan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</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 Fourth Workshop on Text Simplification, Accessibility and Readability (TSAR 2025)</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">Fernando</namePart>
<namePart type="family">Alva-Manchego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</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">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nouran</namePart>
<namePart type="family">Khallaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akio</namePart>
<namePart type="family">Hayakawa</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">979-8-89176-176-6</identifier>
</relatedItem>
<abstract>This paper presents the findings of the first Shared Task on Readability-Controlled Text Simplification at TSAR 2025. The task required systems to simplify English texts to specific target readability levels of the Common European Framework of Reference for Languages (CEFR). We received 48 submissions from 20 participating teams, with approaches predominantly based on large language models (LLMs), which included iterative refinement, multi-agent setups, and LLM-as-a-judge pipelines. For this shared task, we developed a new dataset of pedagogical texts and evaluated submissions using a weighted combination of semantic similarity and CEFR-level accuracy. The results of the participating teams demonstrate that while LLMs can perform substantially well on this task, dependable and controlled simplification often requires complex, multi-iterative processes. Our findings also suggest that the capabilities of current systems are beginning to saturate existing automatic evaluation metrics, underscoring the need for reevaluation and practicality.</abstract>
<identifier type="citekey">alva-manchego-etal-2025-findings</identifier>
<location>
<url>https://aclanthology.org/2025.tsar-1.8/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>116</start>
<end>130</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Findings of the TSAR 2025 Shared Task on Readability-Controlled Text Simplification
%A Alva-Manchego, Fernando
%A Stodden, Regina
%A Imperial, Joseph Marvin
%A Barayan, Abdullah
%A North, Kai
%A Tayyar Madabushi, Harish
%Y Shardlow, Matthew
%Y Alva-Manchego, Fernando
%Y North, Kai
%Y Stodden, Regina
%Y Saggion, Horacio
%Y Khallaf, Nouran
%Y Hayakawa, Akio
%S Proceedings of the Fourth Workshop on Text Simplification, Accessibility and Readability (TSAR 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-176-6
%F alva-manchego-etal-2025-findings
%X This paper presents the findings of the first Shared Task on Readability-Controlled Text Simplification at TSAR 2025. The task required systems to simplify English texts to specific target readability levels of the Common European Framework of Reference for Languages (CEFR). We received 48 submissions from 20 participating teams, with approaches predominantly based on large language models (LLMs), which included iterative refinement, multi-agent setups, and LLM-as-a-judge pipelines. For this shared task, we developed a new dataset of pedagogical texts and evaluated submissions using a weighted combination of semantic similarity and CEFR-level accuracy. The results of the participating teams demonstrate that while LLMs can perform substantially well on this task, dependable and controlled simplification often requires complex, multi-iterative processes. Our findings also suggest that the capabilities of current systems are beginning to saturate existing automatic evaluation metrics, underscoring the need for reevaluation and practicality.
%U https://aclanthology.org/2025.tsar-1.8/
%P 116-130
Markdown (Informal)
[Findings of the TSAR 2025 Shared Task on Readability-Controlled Text Simplification](https://aclanthology.org/2025.tsar-1.8/) (Alva-Manchego et al., TSAR 2025)
ACL