@inproceedings{papucci-etal-2026-controllable,
title = "Controllable Sentence Simplification in {I}talian: Fine-Tuning Large Language Models on Automatically Generated Resources",
author = "Papucci, Michele and
Venturi, Giulia and
Dell{'}Orletta, Felice",
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-1.570/",
doi = "10.63317/5fgm358dfxt5",
pages = "7178--7191",
abstract = "This paper presents a study on readability-controlled Sentence Simplification for Italian, addressing the scarcity of annotated resources for low-resource languages. We introduce IMPaCTS (Italian Multilevel Parallel Corpus for Text Simplification), the first fully automatically created corpus of 1,444,160 original{--}simple sentence pairs automatically annotated with readability levels and linguistic features. It was generated using an Italian LLM prompted in zero-shot to produce multiple simplifications per input sentence. Increasing portions of the resource are used to fine-tune mono- and multilingual open-weight LLMs, conditioning them to generate simplifications at a target readability level. Results from automatic and human evaluations show that fine-tuning on IMPaCTS improves performance both in terms of task completion and adherence to the targeted readability levels compared to few-shot baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="papucci-etal-2026-controllable">
<titleInfo>
<title>Controllable Sentence Simplification in Italian: Fine-Tuning Large Language Models on Automatically Generated Resources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Papucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giulia</namePart>
<namePart type="family">Venturi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</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>This paper presents a study on readability-controlled Sentence Simplification for Italian, addressing the scarcity of annotated resources for low-resource languages. We introduce IMPaCTS (Italian Multilevel Parallel Corpus for Text Simplification), the first fully automatically created corpus of 1,444,160 original–simple sentence pairs automatically annotated with readability levels and linguistic features. It was generated using an Italian LLM prompted in zero-shot to produce multiple simplifications per input sentence. Increasing portions of the resource are used to fine-tune mono- and multilingual open-weight LLMs, conditioning them to generate simplifications at a target readability level. Results from automatic and human evaluations show that fine-tuning on IMPaCTS improves performance both in terms of task completion and adherence to the targeted readability levels compared to few-shot baselines.</abstract>
<identifier type="citekey">papucci-etal-2026-controllable</identifier>
<identifier type="doi">10.63317/5fgm358dfxt5</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.570/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7178</start>
<end>7191</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Controllable Sentence Simplification in Italian: Fine-Tuning Large Language Models on Automatically Generated Resources
%A Papucci, Michele
%A Venturi, Giulia
%A Dell’Orletta, Felice
%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 papucci-etal-2026-controllable
%X This paper presents a study on readability-controlled Sentence Simplification for Italian, addressing the scarcity of annotated resources for low-resource languages. We introduce IMPaCTS (Italian Multilevel Parallel Corpus for Text Simplification), the first fully automatically created corpus of 1,444,160 original–simple sentence pairs automatically annotated with readability levels and linguistic features. It was generated using an Italian LLM prompted in zero-shot to produce multiple simplifications per input sentence. Increasing portions of the resource are used to fine-tune mono- and multilingual open-weight LLMs, conditioning them to generate simplifications at a target readability level. Results from automatic and human evaluations show that fine-tuning on IMPaCTS improves performance both in terms of task completion and adherence to the targeted readability levels compared to few-shot baselines.
%R 10.63317/5fgm358dfxt5
%U https://aclanthology.org/2026.lrec-1.570/
%U https://doi.org/10.63317/5fgm358dfxt5
%P 7178-7191
Markdown (Informal)
[Controllable Sentence Simplification in Italian: Fine-Tuning Large Language Models on Automatically Generated Resources](https://aclanthology.org/2026.lrec-1.570/) (Papucci et al., LREC 2026)
ACL