@inproceedings{hayakawa-etal-2025-towards,
title = "Towards Trustworthy Lexical Simplification: Exploring Safety and Efficiency with Small {LLM}s",
author = "Hayakawa, Akio and
Bott, Stefan and
Saggion, Horacio",
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.15/",
pages = "215--231",
abstract = "Despite their strong performance, large language models (LLMs) face challenges in real-world application of lexical simplification (LS), particularly in privacy-sensitive and resource-constrained environments. Moreover, since vulnerable user groups (e.g., people with disabilities) are one of the key target groups of this technology, it is crucial to ensure the safety and correctness of the output of LS systems. To address these issues, we propose an efficient framework for LS systems that utilizes small LLMs deployable in local environments. Within this framework, we explore knowledge distillation with synthesized data and in-context learning as baselines. Our experiments in five languages evaluate model outputs both automatically and manually. Our manual analysis reveals that while knowledge distillation boosts automatic metric scores, it also introduces a safety trade-off by increasing harmful simplifications. Importantly, we find that the model{'}s output probability is a useful signal for detecting harmful simplifications. Leveraging this, we propose a filtering strategy that suppresses harmful simplifications while largely preserving beneficial ones. This work establishes a benchmark for efficient and safe LS with small LLMs. It highlights the key trade-offs between performance, efficiency, and safety, and demonstrates a promising approach for safe real-world deployment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hayakawa-etal-2025-towards">
<titleInfo>
<title>Towards Trustworthy Lexical Simplification: Exploring Safety and Efficiency with Small LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akio</namePart>
<namePart type="family">Hayakawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Bott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</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>Despite their strong performance, large language models (LLMs) face challenges in real-world application of lexical simplification (LS), particularly in privacy-sensitive and resource-constrained environments. Moreover, since vulnerable user groups (e.g., people with disabilities) are one of the key target groups of this technology, it is crucial to ensure the safety and correctness of the output of LS systems. To address these issues, we propose an efficient framework for LS systems that utilizes small LLMs deployable in local environments. Within this framework, we explore knowledge distillation with synthesized data and in-context learning as baselines. Our experiments in five languages evaluate model outputs both automatically and manually. Our manual analysis reveals that while knowledge distillation boosts automatic metric scores, it also introduces a safety trade-off by increasing harmful simplifications. Importantly, we find that the model’s output probability is a useful signal for detecting harmful simplifications. Leveraging this, we propose a filtering strategy that suppresses harmful simplifications while largely preserving beneficial ones. This work establishes a benchmark for efficient and safe LS with small LLMs. It highlights the key trade-offs between performance, efficiency, and safety, and demonstrates a promising approach for safe real-world deployment.</abstract>
<identifier type="citekey">hayakawa-etal-2025-towards</identifier>
<location>
<url>https://aclanthology.org/2025.inlg-main.15/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>215</start>
<end>231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Trustworthy Lexical Simplification: Exploring Safety and Efficiency with Small LLMs
%A Hayakawa, Akio
%A Bott, Stefan
%A Saggion, Horacio
%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 hayakawa-etal-2025-towards
%X Despite their strong performance, large language models (LLMs) face challenges in real-world application of lexical simplification (LS), particularly in privacy-sensitive and resource-constrained environments. Moreover, since vulnerable user groups (e.g., people with disabilities) are one of the key target groups of this technology, it is crucial to ensure the safety and correctness of the output of LS systems. To address these issues, we propose an efficient framework for LS systems that utilizes small LLMs deployable in local environments. Within this framework, we explore knowledge distillation with synthesized data and in-context learning as baselines. Our experiments in five languages evaluate model outputs both automatically and manually. Our manual analysis reveals that while knowledge distillation boosts automatic metric scores, it also introduces a safety trade-off by increasing harmful simplifications. Importantly, we find that the model’s output probability is a useful signal for detecting harmful simplifications. Leveraging this, we propose a filtering strategy that suppresses harmful simplifications while largely preserving beneficial ones. This work establishes a benchmark for efficient and safe LS with small LLMs. It highlights the key trade-offs between performance, efficiency, and safety, and demonstrates a promising approach for safe real-world deployment.
%U https://aclanthology.org/2025.inlg-main.15/
%P 215-231
Markdown (Informal)
[Towards Trustworthy Lexical Simplification: Exploring Safety and Efficiency with Small LLMs](https://aclanthology.org/2025.inlg-main.15/) (Hayakawa et al., INLG 2025)
ACL