@inproceedings{maekawa-etal-2026-parallel,
title = "Parallel Corpus Filtering Based on Semantic Similarity and Surface Dissimilarity for {J}apanese Text Simplification with {LLM}s",
author = "Maekawa, Daisuke and
Kajiwara, Tomoyuki and
Ninomiya, Takashi",
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-1.86/",
doi = "10.63317/2o26gctx8fej",
pages = "1110--1116",
abstract = "We are focusing on low-cost fine-tuning for large language models (LLMs) in Japanese text simplification. LLMs have achieved high performance even with fine-tuning on small parallel corpora in tasks such as machine translation and dialogue response generation. In this study, we propose a method of parallel corpus filtering for text simplification and investigate how much the number of sentence pairs for fine-tuning LLMs can be reduced. Experimental results on Japanese corpora in three domains revealed that the ability to perform text simplification tasks can be acquired even from a very small corpus of 16 to 64 sentence pairs. Although more parallel corpora are needed to acquire domain knowledge, our method outperformed full fine-tuning while reducing the training corpus by approximately 70{\%}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maekawa-etal-2026-parallel">
<titleInfo>
<title>Parallel Corpus Filtering Based on Semantic Similarity and Surface Dissimilarity for Japanese Text Simplification with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daisuke</namePart>
<namePart type="family">Maekawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoyuki</namePart>
<namePart type="family">Kajiwara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takashi</namePart>
<namePart type="family">Ninomiya</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>We are focusing on low-cost fine-tuning for large language models (LLMs) in Japanese text simplification. LLMs have achieved high performance even with fine-tuning on small parallel corpora in tasks such as machine translation and dialogue response generation. In this study, we propose a method of parallel corpus filtering for text simplification and investigate how much the number of sentence pairs for fine-tuning LLMs can be reduced. Experimental results on Japanese corpora in three domains revealed that the ability to perform text simplification tasks can be acquired even from a very small corpus of 16 to 64 sentence pairs. Although more parallel corpora are needed to acquire domain knowledge, our method outperformed full fine-tuning while reducing the training corpus by approximately 70%.</abstract>
<identifier type="citekey">maekawa-etal-2026-parallel</identifier>
<identifier type="doi">10.63317/2o26gctx8fej</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.86/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1110</start>
<end>1116</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parallel Corpus Filtering Based on Semantic Similarity and Surface Dissimilarity for Japanese Text Simplification with LLMs
%A Maekawa, Daisuke
%A Kajiwara, Tomoyuki
%A Ninomiya, Takashi
%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 maekawa-etal-2026-parallel
%X We are focusing on low-cost fine-tuning for large language models (LLMs) in Japanese text simplification. LLMs have achieved high performance even with fine-tuning on small parallel corpora in tasks such as machine translation and dialogue response generation. In this study, we propose a method of parallel corpus filtering for text simplification and investigate how much the number of sentence pairs for fine-tuning LLMs can be reduced. Experimental results on Japanese corpora in three domains revealed that the ability to perform text simplification tasks can be acquired even from a very small corpus of 16 to 64 sentence pairs. Although more parallel corpora are needed to acquire domain knowledge, our method outperformed full fine-tuning while reducing the training corpus by approximately 70%.
%R 10.63317/2o26gctx8fej
%U https://aclanthology.org/2026.lrec-1.86/
%U https://doi.org/10.63317/2o26gctx8fej
%P 1110-1116
Markdown (Informal)
[Parallel Corpus Filtering Based on Semantic Similarity and Surface Dissimilarity for Japanese Text Simplification with LLMs](https://aclanthology.org/2026.lrec-1.86/) (Maekawa et al., LREC 2026)
ACL