{"ID":2868633,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.15640","arxiv_id":"2509.15640","title":"Multilingual LLM Prompting Strategies for Medical English-Vietnamese Machine Translation","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2509.15640","url_pdf":"https://arxiv.org/pdf/2509.15640v2","authors":"[\"Nhu Vo\",\"Nu-Uyen-Phuong Le\",\"Dung D. Le\",\"Massimo Piccardi\",\"Wray Buntine\"]","published":"2025-09-19T06:06:36Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false}