DCD: Domain-Oriented Design for Controlled Retrieval-Augmented Generation

TL;DR

DCD introduces a hierarchical, domain-oriented design for retrieval-augmented generation systems, improving robustness and factual accuracy without altering language models.

Contribution

It proposes a novel hierarchical knowledge structuring and multi-stage routing approach to enhance RAG performance on heterogeneous data and complex queries.

Findings

Improved robustness and factual accuracy in RAG tasks.

Enhanced answer relevance in applied scenarios.

Effective knowledge structuring without modifying language models.

Abstract

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.