@inproceedings{marzona-etal-2025-exploring,
title = "Exploring Paraphrasing Strategies for {CEFR} A1-Level Constraints in {LLM}s",
author = "Marzona, Eugenio and
Goikhman, Maria and
Aprosio, Alessio Palmero and
Zancanaro, Massimo",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.828/",
doi = "10.18653/v1/2025.findings-emnlp.828",
pages = "15305--15318",
ISBN = "979-8-89176-335-7",
abstract = "Large language models are increasingly used for teaching and self-learning foreign languages. However, their capability to meet specific linguistic constraints is still underexplored. This study compares the effectiveness of prompt engineering in guiding ChatGPT (4o and 4o-mini), and Llama 3 to rephrase general-domain texts to meet CEFR A1-level constraints in English and Italian, making them suitable for beginner learners. It compares 4 prompt engineering approaches, built upon iterative paraphrasing method that gradually refines original texts for CEFR compliance. The approaches compared include paraphrasing with or without Chain-of-Thought, as well as grammar and vocabulary simplification performed either simultaneously or as separate steps. The findings suggest that for English the best approach is combining COT with separate grammar and vocabulary simplification, while for Italian one-step strategies have better effect on grammar, and two-step strategies work better for covering the vocabulary. The paraphrasing approach can approve compliance, although at this point it is not cost-effective. We release a dataset of pairs original sentence-beginner level paraphrase (both in Italian and in English) on which further work could be based."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marzona-etal-2025-exploring">
<titleInfo>
<title>Exploring Paraphrasing Strategies for CEFR A1-Level Constraints in LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eugenio</namePart>
<namePart type="family">Marzona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Goikhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessio</namePart>
<namePart type="given">Palmero</namePart>
<namePart type="family">Aprosio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Zancanaro</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>Findings of the Association for Computational Linguistics: EMNLP 2025</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">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Large language models are increasingly used for teaching and self-learning foreign languages. However, their capability to meet specific linguistic constraints is still underexplored. This study compares the effectiveness of prompt engineering in guiding ChatGPT (4o and 4o-mini), and Llama 3 to rephrase general-domain texts to meet CEFR A1-level constraints in English and Italian, making them suitable for beginner learners. It compares 4 prompt engineering approaches, built upon iterative paraphrasing method that gradually refines original texts for CEFR compliance. The approaches compared include paraphrasing with or without Chain-of-Thought, as well as grammar and vocabulary simplification performed either simultaneously or as separate steps. The findings suggest that for English the best approach is combining COT with separate grammar and vocabulary simplification, while for Italian one-step strategies have better effect on grammar, and two-step strategies work better for covering the vocabulary. The paraphrasing approach can approve compliance, although at this point it is not cost-effective. We release a dataset of pairs original sentence-beginner level paraphrase (both in Italian and in English) on which further work could be based.</abstract>
<identifier type="citekey">marzona-etal-2025-exploring</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.828</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.828/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>15305</start>
<end>15318</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Paraphrasing Strategies for CEFR A1-Level Constraints in LLMs
%A Marzona, Eugenio
%A Goikhman, Maria
%A Aprosio, Alessio Palmero
%A Zancanaro, Massimo
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F marzona-etal-2025-exploring
%X Large language models are increasingly used for teaching and self-learning foreign languages. However, their capability to meet specific linguistic constraints is still underexplored. This study compares the effectiveness of prompt engineering in guiding ChatGPT (4o and 4o-mini), and Llama 3 to rephrase general-domain texts to meet CEFR A1-level constraints in English and Italian, making them suitable for beginner learners. It compares 4 prompt engineering approaches, built upon iterative paraphrasing method that gradually refines original texts for CEFR compliance. The approaches compared include paraphrasing with or without Chain-of-Thought, as well as grammar and vocabulary simplification performed either simultaneously or as separate steps. The findings suggest that for English the best approach is combining COT with separate grammar and vocabulary simplification, while for Italian one-step strategies have better effect on grammar, and two-step strategies work better for covering the vocabulary. The paraphrasing approach can approve compliance, although at this point it is not cost-effective. We release a dataset of pairs original sentence-beginner level paraphrase (both in Italian and in English) on which further work could be based.
%R 10.18653/v1/2025.findings-emnlp.828
%U https://aclanthology.org/2025.findings-emnlp.828/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.828
%P 15305-15318
Markdown (Informal)
[Exploring Paraphrasing Strategies for CEFR A1-Level Constraints in LLMs](https://aclanthology.org/2025.findings-emnlp.828/) (Marzona et al., Findings 2025)
ACL