arXiv Open Access 2025

ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry

Qinwen Chen Wenbiao Tao Zhiwei Zhu Mingfan Xi Liangzhong Guo +3 lainnya
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (8)

Q

Qinwen Chen

W

Wenbiao Tao

Z

Zhiwei Zhu

M

Mingfan Xi

L

Liangzhong Guo

Y

Yuan Wang

W

Wei Wang

Y

Yunshi Lan

Format Sitasi

Chen, Q., Tao, W., Zhu, Z., Xi, M., Guo, L., Wang, Y. et al. (2025). ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry. https://arxiv.org/abs/2506.21098

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓