R2Adapter：面向高效混合RAG的路由与重写适配器
原标题：R$^{2}$Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG
AI 摘要
中国科学院计算技术研究所等机构的研究人员提出了R2Adapter，一种轻量级即插即用的路由与重写适配器，用于在混合RAG系统中动态分配查询，在简单查询上使用vanilla RAG，在复杂多跳查询上使用graph-based RAG。R2Adapter通过训练低成本路由器避免依赖LLM进行路由，并对低置信度的图路由查询进行重写以提升检索质量。实验表明，R2Adapter在保持答案准确率的同时，将图RAG的使用率降低了高达59%，且模型无关，可无缝集成到现有RAG流程中。
正文节选
R2Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG Abstract Retrieval-Augmented Generation (RAG) has become a prevailing paradigm for enhancing Large Language Models (LLMs) with non-parametric knowledge. Vanilla RAG efficiently handles simple queries but struggles with relational or multi-hop reasoning. Graph-based RAG alleviates this issue but incurs higher inference complexity and latency. In practice, user queries can differ significantly in their complexity, rendering a fixe