通过分层设计提升RAG在复杂查询下的准确性和稳定性
DCD: Domain-Oriented Design for Controlled Retrieval-Augmented Generation
- 构建领域-语料-文档三级结构，分阶段控制检索与生成范围
- 在合成数据集上显著提升事实准确性与答案相关性
- 适合需要高可靠性的知识增强型问答系统开发者
检索增强生成（RAG）广泛用于将大语言模型与外部知识源结合。然而，在异构语料和多步查询场景下，由于知识表示扁平化且缺乏显式处理流程，传统RAG性能常下降。本文提出DCD（Domain-Collection-Document）架构，一种面向领域的知识结构化设计，无需修改底层语言模型即可控制RAG中的查询处理流程。该方法基于信息空间的层级分解与基于结构化输出的多阶段路由，实现检索与生成范围的渐进式收缩。系统还包含智能分块、混合检索以及集成验证与生成防护机制。我们在合成评估数据集上展示了DCD架构与工作流，并讨论其在鲁棒性、事实准确性与答案相关性方面的改进效果。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) is widely used to ground large language models in external knowledge sources. However, when applied to heterogeneous corpora and multi-step queries, Naive RAG pipelines often degrade in quality due to flat knowledge representations and the absence of explicit workflows. In this work, we introduce DCD (Domain-Collection-Document), a domain-oriented design to structure knowledge and control query processing in RAG systems without modifying the underlying language model. The proposed approach relies on a hierarchical decomposition of the information space and multi-stage routing based on structured model outputs, enabling progressive restriction of both retrieval and generation scopes. The architecture is complemented by smart chunking, hybrid retrieval, and integrated validation and generation guardrail mechanisms. We describe the DCD architecture and workflow and discuss evaluation results on synthetic evaluation dataset, highlighting their impact on robustness, factual accuracy, and answer relevance in applied RAG scenarios.
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。