超越向量搜索：对比经典RAG与混合GraphRAG在气候科学问答中的表现
Beyond Vector Search: Comparing Classical RAG with Hybrid GraphRAG for Climate Science Q\&A
浏览论文内容
中文总结 AI 辅助
针对传统RAG无法捕捉科学语料概念层级关系的问题，提出整合向量搜索、GraphRAG等的混合架构，在气候科学问答中相比经典RAG实现相关性与召回率大幅提升，为分散科学文献的高效问答系统提供新方向。
中文摘要 AI 辅助
传统检索增强生成（RAG）系统孤立处理文档，无法捕捉复杂科学语料库中概念间的层级关系，这一局限会降低气候学等专业领域的答案质量，这类领域中概念依赖常跨多篇文章。我们提出一种混合架构，整合向量搜索、GraphRAG、Leiden社区检测及交叉编码器重排序，相比经典RAG，其上下文相关性提升160%，上下文召回率提升177%。这些结果表明，融合局部与全局检索显著优于文本片段孤立处理，为针对分散科学文献的更高效问答系统铺平了道路。
英文摘要
Traditional Retrieval-Augmented Generation (RAG) systems treat documents in isolation, failing to capture hierarchical relationships between concepts in complex scientific corpora. This limitation compromises answer quality in specialized domains such as climatology, where conceptual dependencies frequently traverse multiple articles. We propose a hybrid architecture that integrates vector search with GraphRAG, Leiden community detection, and cross-encoder re-ranking, achieving gains of 160\% in contextual relevance and 177\% in contextual recall compared to classical RAG. These results demonstrate that unifying local and global retrieval significantly outperforms text-span isolation, paving the way for more effective question-answering systems over dispersed scientific literature.
发表机构
- Universidade Federal do Pará（帕拉联邦大学）
- Instituto Tecnológico Vale（瓦利技术研究所）
机构由 AI 辅助整理，请以论文原文为准。
