paper-with-me

홈 › Papers

Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources

2024-09-18 · Issey Sukeda

The recent success of large language models (LLMs) and the scaling law has led to a widespread adoption of larger models. Particularly in the healthcare industry, there is an increasing demand for locally operated LLMs due to security concerns. However, the majority of high quality open-source LLMs have a size of 70B parameters, imposing significant financial burdens on users for GPU preparation and operation. To overcome these issues, we present a medical adaptation based on the recent 7B models, which enables the operation in low computational resources. We compare the performance on medical question-answering benchmarks in two languages (Japanese and English), demonstrating that its scores reach parity with or surpass those of currently existing medical LLMs that are ten times larger. We find that fine-tuning an English-centric base model on Japanese medical dataset improves the score in both language, supporting the effect of cross-lingual knowledge transfer. We hope that this study will alleviate financial challenges, serving as a stepping stone for clinical institutions to practically utilize LLMs locally. Our evaluation code is available at https://github.com/stardust-coder/japanese-lm-med-harness.

📄 PDF Abstract BibTeX arXiv:2409.11783

Code (1)

stardust-coder/japanese-lm-med-harness 공식 구현 pytorch

Tasks

GPULanguage ModelingLanguage ModellingLarge Language ModelMedical Question AnsweringQuestion AnsweringTransfer Learning

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

JMedBench: A Benchmark for Evaluating Japanese Biomedical Large Language Models

2024-09-20 · Junfeng Jiang, Jiahao Huang, Akiko Aizawa

Recent developments in Japanese large language models (LLMs) primarily focus on general domains, with fewer advancements in Japanese biomedical LLMs. One obstacle is the absence of a comprehensive, large-scale benchmark …

Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of English-Japanese Biomedical Adaptation

2025-10-14 · Xin Zhao, Naoki Yoshinaga, Yuma Tsuta, Akiko Aizawa arxiv

Multilingual domain adaptation (ML-DA) is widely used to learn new domain knowledge across languages into large language models (LLMs). Although many methods have been proposed to improve domain adaptation, the mechanism…

Cross-Lingual TransferDomain Adaptation

Design Challenges in Named Entity Transliteration

2018-08-07 · COLING 2018 8 · Yuval Merhav, Stephen Ash

We analyze some of the fundamental design challenges that impact the development of a multilingual state-of-the-art named entity transliteration system, including curating bilingual named entity datasets and evaluation o…

DecoderTransliteration

Character-level Japanese Text Generation with Attention Mechanism for Chest Radiography Diagnosis

2020-04-06 · Kenya Sakka, Kotaro Nakayama, Nisei Kimura, Taiki Inoue 외

Chest radiography is a general method for diagnosing a patient's condition and identifying important information; therefore, radiography is used extensively in routine medical practice in various situations, such as emer…

Text Generation

Development of a classifiers/quantifiers dictionary towards French-Japanese MT

2019-02-21 · MTSummit 2017 9 · Mutsuko Tomokiyo, Mathieu Mangeot, Christian Boitet

Although classifiers/quantifiers (CQs) expressions appear frequently in everyday communications or written documents, they are described neither in classical bilingual paper dictionaries , nor in machine-readable diction…

Machine TranslationTranslation