@article{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",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.86/",
    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{\%}."
}