@inproceedings{meng-yang-2026-simple,
title = "{SIMPLE}: A Comparative Study of Prompting and Fine-Tuning for {LLM}-Based Text Simplification",
author = "Meng, Zixian and
Yang, Dongqiang",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2306/",
pages = "52403--52424",
ISBN = "979-8-89176-459-0",
abstract = "Fine-tuning and prompting are two widely used approaches for adapting large language models to downstream tasks. However, their effectiveness on text simplification remains underexplored. We present SIMPLE, a comprehensive evaluation of large language model-based sentence simplification. We evaluate 12 open-weight large language models across diverse domains, including Wikipedia, medical, scientific, and news texts. In addition to standard evaluation metrics, we conduct a linguistic analysis of simplification outputs at the lexical, syntactic, and discourse levels. Our findings show that: 1) under practical deployment settings, QLoRA fine-tuning of base models performs better on Wikipedia-based simplification, whereas optimized prompting of instruction-tuned models performs better in non-Wikipedia domains; 2) QLoRA-fine-tuned models exhibit a strong alignment with human-written references across target readability levels, while prompted models show limited controllability over output difficulty; and 3) the primary discrepancies between large language model-generated simplifications and human references arise from syntactic restructuring and discourse coherence."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meng-yang-2026-simple">
<titleInfo>
<title>SIMPLE: A Comparative Study of Prompting and Fine-Tuning for LLM-Based Text Simplification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zixian</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongqiang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Fine-tuning and prompting are two widely used approaches for adapting large language models to downstream tasks. However, their effectiveness on text simplification remains underexplored. We present SIMPLE, a comprehensive evaluation of large language model-based sentence simplification. We evaluate 12 open-weight large language models across diverse domains, including Wikipedia, medical, scientific, and news texts. In addition to standard evaluation metrics, we conduct a linguistic analysis of simplification outputs at the lexical, syntactic, and discourse levels. Our findings show that: 1) under practical deployment settings, QLoRA fine-tuning of base models performs better on Wikipedia-based simplification, whereas optimized prompting of instruction-tuned models performs better in non-Wikipedia domains; 2) QLoRA-fine-tuned models exhibit a strong alignment with human-written references across target readability levels, while prompted models show limited controllability over output difficulty; and 3) the primary discrepancies between large language model-generated simplifications and human references arise from syntactic restructuring and discourse coherence.</abstract>
<identifier type="citekey">meng-yang-2026-simple</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2306/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>52403</start>
<end>52424</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SIMPLE: A Comparative Study of Prompting and Fine-Tuning for LLM-Based Text Simplification
%A Meng, Zixian
%A Yang, Dongqiang
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F meng-yang-2026-simple
%X Fine-tuning and prompting are two widely used approaches for adapting large language models to downstream tasks. However, their effectiveness on text simplification remains underexplored. We present SIMPLE, a comprehensive evaluation of large language model-based sentence simplification. We evaluate 12 open-weight large language models across diverse domains, including Wikipedia, medical, scientific, and news texts. In addition to standard evaluation metrics, we conduct a linguistic analysis of simplification outputs at the lexical, syntactic, and discourse levels. Our findings show that: 1) under practical deployment settings, QLoRA fine-tuning of base models performs better on Wikipedia-based simplification, whereas optimized prompting of instruction-tuned models performs better in non-Wikipedia domains; 2) QLoRA-fine-tuned models exhibit a strong alignment with human-written references across target readability levels, while prompted models show limited controllability over output difficulty; and 3) the primary discrepancies between large language model-generated simplifications and human references arise from syntactic restructuring and discourse coherence.
%U https://aclanthology.org/2026.emnlp-main.2306/
%P 52403-52424
Markdown (Informal)
[SIMPLE: A Comparative Study of Prompting and Fine-Tuning for LLM-Based Text Simplification](https://aclanthology.org/2026.emnlp-main.2306/) (Meng & Yang, EMNLP 2026)
ACL