发表机构
RWTH Aachen University; University Hospital RWTH Aachen（亚琛RWTH大学; 亚琛RWTH大学医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对现有RAG方法缺乏结构化公平化的问题，引入公平的GraphRAG框架，以公平数字对象为基本单元，利用大语言模型支持相关构建与提取，应用于生物医学数据集，显著提升问答效果，展示了公平数据实践与图检索技术结合的可行性。
AI 中文摘要
检索增强生成（RAG）解决了大语言模型在回答特定领域问题时的局限性。基于图的RAG方法，如图GraphRAG，通过捕获知识图谱中的语义关系来增强检索。虽然公平原则在科学数据管理中变得普遍，但现有RAG方法缺乏对基础知识资源的结构化公平化。为解决这一差距，我们引入了公平的GraphRAG，它将公平数字对象作为基于图的检索系统的基本单元。我们利用大语言模型支持模式构建和从数据源自动提取内容及元数据。该框架由医生和计算机科学家共同设计。我们将其应用于胃肠病学的生物医学数据集，证明了其对RNA测序数据的适用性。公平的GraphRAG显著提高了问答准确性、覆盖范围和可解释性，尤其对于涉及元数据和本体链接的复杂查询。这项工作展示了将公平数据实践与基于图的检索技术相结合的可行性。
英文摘要
Retrieval-Augmented Generation (RAG) addresses the limitations of Large Language Models (LLMs) when providing responses to domain-specific questions. Graph-based RAG approaches, such as GraphRAG, enhance retrieval by capturing semantic relationships within knowledge graphs (KGs). While the FAIR principles (Findability, Accessibility, Interoperability, and Reusability) are becoming prevalent for scientific data management, especially in complex domains such as medicine, existing RAG approaches lack a structured FAIRification of the underlying knowledge resources. This lack limits their potential for FAIR information retrieval in these domains. To address this gap, we introduce FAIR GraphRAG, a novel framework that integrates FAIR Digital Objects (FDOs) as the fundamental units of a graph-based retrieval system. Each graph node represents an FDO that incorporates core data, metadata, persistent identifiers, and semantic links. We leverage LLMs to support schema construction and automated extraction of content and metadata from data sources. The framework was co-designed by physicians and computer scientists to ensure technical and clinical relevance. We apply FAIR GraphRAG to a biomedical dataset in gastroenterology, demonstrating its applicability to RNA-sequencing data. Beyond ensuring adherence to the FAIR principles, FAIR GraphRAG significantly improves question answering accuracy, coverage, and explainability, particularly for complex queries involving metadata and ontology links. This work shows the feasibility of combining FAIR data practices with graph-based retrieval techniques. We see potential for applying our approach to other specialized fields such as education and business.
CommentsAccepted at the IEEE International Conference on Knowledge Graph, 2025. Corrects an error in the published abstract: the evaluation dataset is RNA-sequencing data, not single-cell data
Journal ref2025 IEEE International Conference on Knowledge Graph (ICKG), Limassol, Cyprus, 2025, pp. 90-97
DOI：10.1109/ICKG66886.2025.00019
