MKG-Rank: Enhancing Large Language Models with Knowledge Graph for Multilingual Medical Question Answering
This addresses the critical language gap in medical QA for low-resource languages, though it is an incremental improvement by enhancing existing LLMs with knowledge graphs.
The paper tackles the problem of limited multilingual effectiveness in medical question answering by large language models, proposing MKG-Rank to integrate English-centric knowledge graphs, which achieves up to a 35.03% increase in accuracy and an average retrieval time of 0.0009 seconds across multiple languages.
Large Language Models (LLMs) have shown remarkable progress in medical question answering (QA), yet their effectiveness remains predominantly limited to English due to imbalanced multilingual training data and scarce medical resources for low-resource languages. To address this critical language gap in medical QA, we propose Multilingual Knowledge Graph-based Retrieval Ranking (MKG-Rank), a knowledge graph-enhanced framework that enables English-centric LLMs to perform multilingual medical QA. Through a word-level translation mechanism, our framework efficiently integrates comprehensive English-centric medical knowledge graphs into LLM reasoning at a low cost, mitigating cross-lingual semantic distortion and achieving precise medical QA across language barriers. To enhance efficiency, we introduce caching and multi-angle ranking strategies to optimize the retrieval process, significantly reducing response times and prioritizing relevant medical knowledge. Extensive evaluations on multilingual medical QA benchmarks across Chinese, Japanese, Korean, and Swahili demonstrate that MKG-Rank consistently outperforms zero-shot LLMs, achieving maximum 35.03% increase in accuracy, while maintaining an average retrieval time of only 0.0009 seconds.