70B-parameter large language models in Japanese medical question-answering
Abstract: Since the rise of large language models (LLMs), the domain adaptation has been one of the hot topics in various domains.
Many medical LLMs trained with English medical dataset have made public recently.
However, Japanese LLMs in medical domain still lack its research with difficulties of lacking dataset.
Here we utilize multiple 70B-parameter LLMs for the first time and show that instruction tuning using Japanese medical question-answering dataset significantly improves the ability of Japanese LLMs to solve Japanese medical license exams, surpassing 50\% in accuracy.
In particular, the Japanese-centric models exhibit a more significant leap in improvement through instruction tuning compared to their English-centric counterparts. This underscores the importance of continual pretraining and the adjustment of the tokenizer in our local language.
We also examine two slightly different prompt formats, resulting in non-negligible performance improvement.
Paper Type: Short
Research Area: Question Answering
Research Area Keywords: biomedical QA
Contribution Types: Publicly available software and/or pre-trained models
Languages Studied: Japanese
Section 2 Permission To Publish Peer Reviewers Content Agreement: Authors grant permission for ACL to publish peer reviewers' content
Submission Number: 10
Loading