# Multilingual LLM Prompting Strategies for Medical English-Vietnamese Machine Translation

arXiv: https://arxiv.org/abs/2509.15640 · HTML: https://mlsanity.com/paper/2509.15640/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 19 Sep 2025.

## Builds on (most cited first, 10 of 10)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection](https://mlsanity.com/paper/2310.10482/) (2023)
- [CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2209.06243/) (2022)
- [Large language models in healthcare and medical domain: A review](https://mlsanity.com/paper/2401.06775/) (2023)
- [Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation](https://mlsanity.com/paper/2302.07856/) (2023)
- [How to Design Translation Prompts for ChatGPT: An Empirical Study](https://mlsanity.com/paper/2304.02182/) (2023)
- [Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation](https://mlsanity.com/paper/1409.1257/) (2014)
- [Improving Vietnamese-English Medical Machine Translation](https://mlsanity.com/paper/2403.19161/) (2024)
- [Comparing Large Language Models and Traditional Machine Translation Tools for Translating Medical Consultation Summaries: A Pilot Study](https://mlsanity.com/paper/2504.16601/) (2025)

## Abstract (arXiv)

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.