ACL 2025finding0 citations
Large Vocabulary Size Improves Large Language Models
Sho Takase, Ryokan Ri, Shun Kiyono, Takuya Kato
Abstract
This paper empirically investigates the relationship between subword vocabulary size and the performance of large language models (LLMs) to provide insights on how to define the vocabulary size. Experimental results show that larger vocabulary sizes lead to better performance in LLMs. Moreover, we consider a continual training scenario where a pre-trained language model is trained on a different target language. We introduce a simple method to use a new vocabulary instead of the pre-defined one. We show that using the new vocabulary outperforms the model with the vocabulary used in pre-training.
BibTeX
@inproceedings{takase-etal-2025-large,
title = "Large Vocabulary Size Improves Large Language Models",
author = "Takase, Sho and
Ri, Ryokan and
Kiyono, Shun and
Kato, Takuya",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.57/",
doi = "10.18653/v1/2025.findings-acl.57",
pages = "1015--1026",
ISBN = "979-8-89176-256-5"
}