arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.07590cs.IRcs.AI
收藏

DCD:面向领域的受控检索增强生成设计

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

red_mad_robot

Valerii Kovalskii, Nikita Belov, Nikita Miteyko, Igor Reshetnikov, Maksim Maksimov

AI总结:

提出DCD(领域-集合-文档)层次化设计,通过结构化知识表示和多阶段路由控制检索与生成范围,无需修改语言模型,提升RAG在异构语料和多步查询中的鲁棒性和准确性。

摘要:

检索增强生成(RAG)被广泛用于将大型语言模型锚定在外部知识源中。然而,当应用于异构语料库和多步查询时,朴素RAG管道由于扁平的知识表示和缺乏显式工作流而常常质量下降。在这项工作中,我们引入了DCD(领域-集合-文档),一种面向领域的设计,用于结构化知识并控制RAG系统中的查询处理,而无需修改底层语言模型。所提出的方法依赖于信息空间的层次分解和基于结构化模型输出的多阶段路由,使得检索和生成范围能够逐步受限。该架构辅以智能分块、混合检索以及集成验证和生成护栏机制。我们描述了DCD架构和工作流程,并讨论了在合成评估数据集上的评估结果,突出了它们在应用RAG场景中对鲁棒性、事实准确性和答案相关性的影响。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑