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, Yuan Wang, Wei Wang, Yunshi Lan*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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%–23.3%, and lowering chunk growth from 20.23% to 2.06% over iterations.

Original languageEnglish
Title of host publicationIndustry Track
EditorsGeorg Rehm, Yunyao Li
PublisherAssociation for Computational Linguistics (ACL)
Pages749-763
Number of pages15
ISBN (Electronic)9798891762886
DOIs
StatePublished - 2025
Event63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025 - Vienna, Austria
Duration: 27 Jul 20251 Aug 2025

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume6
ISSN (Print)0736-587X

Conference

Conference63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025
Country/TerritoryAustria
CityVienna
Period27/07/251/08/25

Fingerprint

Dive into the research topics of 'ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry'. Together they form a unique fingerprint.

Cite this