JMIR formative research · 2026
Korean Medical Consultation With Open-Weight Large Language Models: Pilot Comparative Evaluation of Retrieval-Augmented Generation With Metadata Filtering.
Сравнительное исследованиеСтатьяПоддержка исследования: вне правительства СШАНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Choi Saeyoun, Kim Donghyun, Jeon Ji-Hwan, Kim Minji, Lee Dong Hun, Ahn DaeHwan, Lee Eu Sun, Kim Yoon Ji, Youk Hyun
Аннотация
BACKGROUND: This study develops an open-source large language model-based chatbot tailored for Korean health consultations. The chatbot was implemented using the retrieval-augmented generation (RAG) technique alongside metadata filtering to enhance its performance.
OBJECTIVE: This study aims to analyze and compare the performance of a RAG-based chatbot with other leading language models in the context of Korean health consultations.
METHODS: A 10.4 GB Korean medical document corpus (487,277 segments) was constructed from official websites of major Korean hospitals, public health sources, and medical textbooks. This study quantitatively compared 5 open-source large language models (Qwen3:4B, Mistral:7B, Llama-3.1:8B, Gpt-Oss:20B, and Gemma3:27B) in 3 configurations: baseline (model only), RAG-only, and RAG with metadata filtering. The RAG system used a specialized Korean embedding model (upskyy/bge-m3-korean) and an Elasticsearch store. Performance was assessed by an emergency medicine specialist using a validation set of 226 questions across 7 common diseases and scoring responses based on accuracy, safety, and helpfulness.
RESULTS: The application of RAG alone failed to yield statistically significant performance improvements and, in some cases (Llama 3.1: 8B and Gemma 3: 27B), resulted in decreased scores. However, the combination of RAG with metadata filtering yielded statistically significant (P<.05) performance increases in most models. Notably, the average score for Mistral:7B increased from 3.79, SD 0.08, to 4.10, SD 0.10, and Gpt-Oss:20B increased from 4.43, SD 0.05, to 4.51, SD 0.04, with the latter achieving the highest safety score (4.61, SD 0.03). The Gemma3:27B model, which possessed a high baseline performance (4.42, SD 0.03), was an exception, exhibiting no significant improvement (P=.14) even with filtering.
CONCLUSIONS: The effectiveness of RAG for specialized domains such as Korean medical consultation is highly dependent on a metadata filtering process that controls the quality of retrieved information; simple information augmentation is insufficient. Furthermore, the benefit of RAG is limited when a model's intrinsic knowledge (eg, Gemma3:27B) already meets or exceeds the quality of the external knowledge base. This finding indicates that performance enhancement strategies must account for both the retrieval mechanism's quality and the model's preexisting capabilities.
OBJECTIVE: This study aims to analyze and compare the performance of a RAG-based chatbot with other leading language models in the context of Korean health consultations.
METHODS: A 10.4 GB Korean medical document corpus (487,277 segments) was constructed from official websites of major Korean hospitals, public health sources, and medical textbooks. This study quantitatively compared 5 open-source large language models (Qwen3:4B, Mistral:7B, Llama-3.1:8B, Gpt-Oss:20B, and Gemma3:27B) in 3 configurations: baseline (model only), RAG-only, and RAG with metadata filtering. The RAG system used a specialized Korean embedding model (upskyy/bge-m3-korean) and an Elasticsearch store. Performance was assessed by an emergency medicine specialist using a validation set of 226 questions across 7 common diseases and scoring responses based on accuracy, safety, and helpfulness.
RESULTS: The application of RAG alone failed to yield statistically significant performance improvements and, in some cases (Llama 3.1: 8B and Gemma 3: 27B), resulted in decreased scores. However, the combination of RAG with metadata filtering yielded statistically significant (P<.05) performance increases in most models. Notably, the average score for Mistral:7B increased from 3.79, SD 0.08, to 4.10, SD 0.10, and Gpt-Oss:20B increased from 4.43, SD 0.05, to 4.51, SD 0.04, with the latter achieving the highest safety score (4.61, SD 0.03). The Gemma3:27B model, which possessed a high baseline performance (4.42, SD 0.03), was an exception, exhibiting no significant improvement (P=.14) even with filtering.
CONCLUSIONS: The effectiveness of RAG for specialized domains such as Korean medical consultation is highly dependent on a metadata filtering process that controls the quality of retrieved information; simple information augmentation is insufficient. Furthermore, the benefit of RAG is limited when a model's intrinsic knowledge (eg, Gemma3:27B) already meets or exceeds the quality of the external knowledge base. This finding indicates that performance enhancement strategies must account for both the retrieval mechanism's quality and the model's preexisting capabilities.