VietMed-MCQ: A Consistency-Filtered Data Synthesis Framework for Vietnamese Traditional Medicine Evaluation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kiet, Huynh Trung, Minh, Dao Sy Duy, Duong, Nguyen Dinh Ha, Huy, Le Hoang Minh, Nguyen, Long, Dinh, Dien
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915712946143232
author Kiet, Huynh Trung
Minh, Dao Sy Duy
Duong, Nguyen Dinh Ha
Huy, Le Hoang Minh
Nguyen, Long
Dinh, Dien
author_facet Kiet, Huynh Trung
Minh, Dao Sy Duy
Duong, Nguyen Dinh Ha
Huy, Le Hoang Minh
Nguyen, Long
Dinh, Dien
contents Large Language Models (LLMs) have demonstrated remarkable proficiency in general medical domains. However, their performance significantly degrades in specialized, culturally specific domains such as Vietnamese Traditional Medicine (VTM), primarily due to the scarcity of high-quality, structured benchmarks. In this paper, we introduce VietMed-MCQ, a novel multiple-choice question dataset generated via a Retrieval-Augmented Generation (RAG) pipeline with an automated consistency check mechanism. Unlike previous synthetic datasets, our framework incorporates a dual-model validation approach to ensure reasoning consistency through independent answer verification, though the substring-based evidence checking has known limitations. The complete dataset of 3,190 questions spans three difficulty levels and underwent validation by one medical expert and four students, achieving 94.2 percent approval with substantial inter-rater agreement (Fleiss' kappa = 0.82). We benchmark seven open-source models on VietMed-MCQ. Results reveal that general-purpose models with strong Chinese priors outperform Vietnamese-centric models, highlighting cross-lingual conceptual transfer, while all models still struggle with complex diagnostic reasoning. Our code and dataset are publicly available to foster research in low-resource medical domains.
format Preprint
id arxiv_https___arxiv_org_abs_2601_03792
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VietMed-MCQ: A Consistency-Filtered Data Synthesis Framework for Vietnamese Traditional Medicine Evaluation
Kiet, Huynh Trung
Minh, Dao Sy Duy
Duong, Nguyen Dinh Ha
Huy, Le Hoang Minh
Nguyen, Long
Dinh, Dien
Computation and Language
68T50
I.2.7; J.3
Large Language Models (LLMs) have demonstrated remarkable proficiency in general medical domains. However, their performance significantly degrades in specialized, culturally specific domains such as Vietnamese Traditional Medicine (VTM), primarily due to the scarcity of high-quality, structured benchmarks. In this paper, we introduce VietMed-MCQ, a novel multiple-choice question dataset generated via a Retrieval-Augmented Generation (RAG) pipeline with an automated consistency check mechanism. Unlike previous synthetic datasets, our framework incorporates a dual-model validation approach to ensure reasoning consistency through independent answer verification, though the substring-based evidence checking has known limitations. The complete dataset of 3,190 questions spans three difficulty levels and underwent validation by one medical expert and four students, achieving 94.2 percent approval with substantial inter-rater agreement (Fleiss' kappa = 0.82). We benchmark seven open-source models on VietMed-MCQ. Results reveal that general-purpose models with strong Chinese priors outperform Vietnamese-centric models, highlighting cross-lingual conceptual transfer, while all models still struggle with complex diagnostic reasoning. Our code and dataset are publicly available to foster research in low-resource medical domains.
title VietMed-MCQ: A Consistency-Filtered Data Synthesis Framework for Vietnamese Traditional Medicine Evaluation
topic Computation and Language
68T50
I.2.7; J.3
url https://arxiv.org/abs/2601.03792