arXiv 2603.239892026-03-25cs.CL

CoCR-RAG：通过面向概念的上下文重建提升Web问答中的检索增强生成

CoCR-RAG: Enhancing Retrieval-Augmented Generation in Web Q&A via Concept-oriented Context Reconstruction

University of Southern Queensland（昆士兰大学）；University of Technology Sydney（新南威尔士大学）；The Hong Kong Polytechnic University（香港理工大学）；National University of Singapore（新加坡国立大学）；Qatar Computing Research Institute（卡塔尔计算研究所）；The Education University of Hong Kong（香港教育大学）

Kaize Shi, Xueyao Sun, Qika Lin, Firoj Alam, Qing Li, Xiaohui Tao, Guandong Xu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出CoCR-RAG框架，通过语言学基础的概念级整合解决多源信息融合问题，提升问答系统事实一致性与知识密度。

摘要：

检索增强生成（RAG）通过整合网络和其他外部信息提升了问答性能。然而，从异构网络检索的文档往往来自多个来源，具有多样的写作风格、格式和粒度。将这些多源文档融合为连贯且知识密集的上下文仍是一个重大挑战，因为无关和冗余信息可能破坏推断答案的事实一致性。本文提出了面向概念的上下文重建RAG（CoCR-RAG），通过语言学基础的概念级整合解决RAG中的多源信息融合问题。具体而言，我们引入了一个概念蒸馏算法，从抽象意义表示（AMR）中提取核心概念，AMR是一种稳定的语义表示，将文本的意义结构化为逻辑图。从多个检索文档中提取的概念随后通过大型语言模型融合和重建为统一的信息密集上下文，仅补充必要的句子元素以突出核心知识。在PopQA和EntityQuestions数据集上的实验表明，CoCR-RAG在这些Web问答基准上显著优于现有上下文重建方法。此外，CoCR-RAG在各种基础LLM上表现出鲁棒性，成为灵活、可插拔的组件，可适应不同的RAG框架。

英文摘要：

Retrieval-augmented generation (RAG) has shown promising results in enhancing Q&A by incorporating information from the web and other external sources. However, the supporting documents retrieved from the heterogeneous web often originate from multiple sources with diverse writing styles, varying formats, and inconsistent granularity. Fusing such multi-source documents into a coherent and knowledge-intensive context remains a significant challenge, as the presence of irrelevant and redundant information can compromise the factual consistency of the inferred answers. This paper proposes the Concept-oriented Context Reconstruction RAG (CoCR-RAG), a framework that addresses the multi-source information fusion problem in RAG through linguistically grounded concept-level integration. Specifically, we introduce a concept distillation algorithm that extracts essential concepts from Abstract Meaning Representation (AMR), a stable semantic representation that structures the meaning of texts as logical graphs. The distilled concepts from multiple retrieved documents are then fused and reconstructed into a unified, information-intensive context by Large Language Models, which supplement only the necessary sentence elements to highlight the core knowledge. Experiments on the PopQA and EntityQuestions datasets demonstrate that CoCR-RAG significantly outperforms existing context-reconstruction methods across these Web Q&A benchmarks. Furthermore, CoCR-RAG shows robustness across various backbone LLMs, establishing itself as a flexible, plug-and-play component adaptable to different RAG frameworks.

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。