动态向量存储增强实时工业问答，提升知识利用与响应效率
ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry
- 用中心点记忆机制融合静态知识与动态历史问答对
- 向量相似度提升25.9%，延迟降低8.7%至23.3%，数据膨胀从20.23%降至2.06%
- 适合需要高效实时问答的工业级社区知识系统
社区问答（CQA）平台可视为社区中的重要知识库，但如何在实时场景下有效利用历史互动与领域知识仍具挑战。现有方法常忽视外部知识，未能融合动态历史问答上下文，或缺乏适合工业部署的记忆机制。本文提出ComRAG，一种面向工业级实时社区问答的检索增强生成框架，通过基于中心点的记忆机制，将静态知识与动态历史问答对融合于检索、生成与高效存储中。在三个工业级CQA数据集上评估，ComRAG持续优于所有基线——向量相似度提升最高达25.9%，延迟降低8.7%至23.3%，迭代过程中分块增长从20.23%降至2.06%。
原文摘要 · Abstract (English)
Community Question Answering (CQA) platforms can be deemed as important knowledge bases in community, but effectively leveraging historical interactions and domain knowledge in real-time remains a challenge. Existing methods often underutilize external knowledge, fail to incorporate dynamic historical QA context, or lack memory mechanisms suited for industrial deployment. We propose ComRAG, a retrieval-augmented generation framework for real-time industrial CQA that integrates static knowledge with dynamic historical QA pairs via a centroid-based memory mechanism designed for retrieval, generation, and efficient storage. Evaluated on three industrial CQA datasets, ComRAG consistently outperforms all baselines--achieving up to 25.9% improvement in vector similarity, reducing latency by 8.7% to 23.3%, and lowering chunk growth from 20.23% to 2.06% over iterations.
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。