Can I read Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities on EtoBox?

Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities by Fujii, Kazuki; Nakamura, Taishi; Loem, Mengsay; Iida, Hiroki; Ohi, Masanari; Hattori, Kakeru; Shota, Hirai; Mizuki, Sakae; Yokota, Rio; Okazaki, Naoaki is a scholarly article available to read on EtoBox.

What is Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities about?

Cross-lingual continual pre-training of large language models (LLMs) initially trained on English corpus allows us to leverage the vast amount of English language resources and reduce the pre-training cost. In this study, we constructed Swallow, an LLM with enhanced Japanese capability, by extending the vocabulary of Llama 2 to include Japanese characters and conducting continual pre-training on a large Japanese web corpus. Experimental results confirmed that the performance on Japanese tasks drastically improved through continual pre-training, and the performance monotonically increased with the amount of training data up to 100B tokens. Consequently, Swallow achieved superior performance compared to other LLMs that were trained from scratch in English and Japanese. An analysis of the effects of continual pre-training revealed that it was particularly effective for Japanese question answering tasks. Furthermore, to elucidate effective methodologies for cross-lingual continual pre-training from English to Japanese, we investigated the impact of vocabulary expansion and the effectiveness of incorporating parallel corpora. The results showed that the efficiency gained through vocabul

Author

Fujii, Kazuki; Nakamura, Taishi; Loem, Mengsay; Iida, Hiroki; Ohi, Masanari; Hattori, Kakeru; Shota, Hirai; Mizuki, Sakae; Yokota, Rio; Okazaki, Naoaki

Published

2024

Language

EN