Multilingual LLM Prompting Strategies for Medical English-Vietnamese Machine Translation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vo, Nhu, Le, Nu-Uyen-Phuong, Le, Dung D., Piccardi, Massimo, Buntine, Wray
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908606596644864
author Vo, Nhu
Le, Nu-Uyen-Phuong
Le, Dung D.
Piccardi, Massimo
Buntine, Wray
author_facet Vo, Nhu
Le, Nu-Uyen-Phuong
Le, Dung D.
Piccardi, Massimo
Buntine, Wray
contents Medical English-Vietnamese machine translation (En-Vi MT) is essential for healthcare access and communication in Vietnam, yet Vietnamese remains a low-resource and under-studied language. We systematically evaluate prompting strategies for six multilingual LLMs (0.5B-9B parameters) on the MedEV dataset, comparing zero-shot, few-shot, and dictionary-augmented prompting with Meddict, an English-Vietnamese medical lexicon. Results show that model scale is the primary driver of performance: larger LLMs achieve strong zero-shot results, while few-shot prompting yields only marginal improvements. In contrast, terminology-aware cues and embedding-based example retrieval consistently improve domain-specific translation. These findings underscore both the promise and the current limitations of multilingual LLMs for medical En-Vi MT.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15640
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multilingual LLM Prompting Strategies for Medical English-Vietnamese Machine Translation
Vo, Nhu
Le, Nu-Uyen-Phuong
Le, Dung D.
Piccardi, Massimo
Buntine, Wray
Computation and Language
Medical English-Vietnamese machine translation (En-Vi MT) is essential for healthcare access and communication in Vietnam, yet Vietnamese remains a low-resource and under-studied language. We systematically evaluate prompting strategies for six multilingual LLMs (0.5B-9B parameters) on the MedEV dataset, comparing zero-shot, few-shot, and dictionary-augmented prompting with Meddict, an English-Vietnamese medical lexicon. Results show that model scale is the primary driver of performance: larger LLMs achieve strong zero-shot results, while few-shot prompting yields only marginal improvements. In contrast, terminology-aware cues and embedding-based example retrieval consistently improve domain-specific translation. These findings underscore both the promise and the current limitations of multilingual LLMs for medical En-Vi MT.
title Multilingual LLM Prompting Strategies for Medical English-Vietnamese Machine Translation
topic Computation and Language
url https://arxiv.org/abs/2509.15640