用知识图谱增强医学大模型问答能力，效果显著且成本低。
MEG: Medical Knowledge-Augmented Large Language Models for Question Answering
- 通过轻量映射网络融合知识图谱嵌入，提升模型推理能力。
- 在四个医学多选题数据集上平均提升6.7%至9.9%准确率。
- 对图编码器选择不敏感，适合实际部署的医疗问答场景。
问答是自然语言理解任务，需基于显式上下文和隐含领域知识进行推理。尽管训练成本高昂，现有大语言模型（LLMs）在医学等专业领域仍难以可靠捕捉概念间的细微关系。本文提出MEG，一种参数高效的医学知识增强型大模型方法。MEG通过轻量级映射网络将知识图谱嵌入融入LLM，以低成本方式利用外部知识。我们在四个主流医学多选题数据集上评估，结果表明：LLMs能有效解析知识图谱嵌入，并显著受益于其提供的事实支撑。相比BioMistral-7B和MediTron-7B等专用模型，MEG分别实现平均+6.7%和+9.9%的准确率提升。此外，MEG性能对图编码器选择具有鲁棒性。
原文摘要 · Abstract (English)
Question answering is a natural language understanding task that involves reasoning over both explicit context, and unstated relevant domain knowledge. Despite the high cost of training, large language models (LLMs) -- the backbone of most modern question-answering systems -- still struggle to reliably capture the nuanced relationships between concepts that are crucial for reasoning in specialized fields like medicine. In this work, we present MEG, a parameter-efficient approach for medical knowledge-augmented LLMs. MEG uses a lightweight mapping network to incorporate knowledge graph embeddings into the LLM, enabling it to leverage external knowledge in a cost-effective way. We evaluate our method on four popular medical multiple-choice datasets and show that LLMs i) can effectively interpret knowledge graph embeddings and ii) gain significant advantages from the factual grounding these embeddings provide. MEG attains an average of +6.7% and +9.9% accuracy over specialized models like BioMistral-7B and MediTron-7B, respectively. Finally, we show that MEG's performance remains robust to the choice of graph encoder.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。