The 265th Natural Language Processing Research Workshop, Sep. 22, 2025
The 265th Natural Language Processing Research Workshop (NL265)
While the development of large language models (LLMs) has dramatically improved performance in natural language processing tasks, optimizing models specifically for translation tasks remains an ongoing challenge. In this study, we propose "plamo-2-translate," a large language model specialized for Japanese-English translation tasks. Our proposed model achieves fluent and contextually appropriate translations by combining specialized input/output control using a dedicated format, fine-tuning with parallel corpora and synthetic data, and optimization through Iterative DPO. Evaluation experiments demonstrate that our model achieves performance comparable to or better than base models and other LLMs across multiple metrics including BLEU, chrF, BERTScore, COMET, and GEMBA-MQM, with particularly significant improvements observed in GEMBA-MQM, which closely aligns with human evaluation standards. Furthermore, the model incorporates features such as style specification and context preservation to cater to diverse translation requirements. The model developed in this study has been made publicly available through Huggingface.
@inproceedings{Imajo2025-nl265,
title={{PLaMo Translate: Development of a Translation-Specialized Large Language Model [in Japanese]}},
author={Kentaro Imajo and Masanori Hirano and Kento Nozawa and Kaizaburo Chubachi},
booktitle={The 265th Natural Language Processing Research Workshop},
url={https://ipsj.ixsq.nii.ac.jp/records/2004363},
year={2025}
}