DCD: Domain-Oriented Design for Controlled Retrieval-Augmented Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917392528965632 |
|---|---|
| author | Kovalskiy, Valeriy Belov, Nikita Miteyko, Nikita Reshetnikov, Igor Maximov, Max |
| author_facet | Kovalskiy, Valeriy Belov, Nikita Miteyko, Nikita Reshetnikov, Igor Maximov, Max |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_07590 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DCD: Domain-Oriented Design for Controlled Retrieval-Augmented Generation Kovalskiy, Valeriy Belov, Nikita Miteyko, Nikita Reshetnikov, Igor Maximov, Max Information Retrieval Artificial Intelligence 68P20 (Primary), 68T50 (Secondary) H.3.3; I.2.7; I.2.4 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. |
| title | DCD: Domain-Oriented Design for Controlled Retrieval-Augmented Generation |
| topic | Information Retrieval Artificial Intelligence 68P20 (Primary), 68T50 (Secondary) H.3.3; I.2.7; I.2.4 |
| url | https://arxiv.org/abs/2604.07590 |