Empowering LLMs by hybrid retrieval-augmented generation for domain-centric Q&A in smart manufacturing

Wan, Yuwei, Chen, Zheyuan, Liu, Ying ORCID: https://orcid.org/0000-0001-9319-5940, Chen, Chong and Packianather, Michael ORCID: https://orcid.org/0000-0002-9436-8206 2025. Empowering LLMs by hybrid retrieval-augmented generation for domain-centric Q&A in smart manufacturing. Advanced Engineering Informatics 65 , 103212. 10.1016/j.aei.2025.103212

Preview

PDF - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (6MB) | Preview

Abstract

Large language models (LLMs) have shown remarkable performances in generic question-answering (QA) but often suffer from domain gaps and outdated knowledge in smart manufacturing (SM). Retrieval-augmented generation (RAG) based on LLMs has emerged as a potential approach by incorporating an external knowledge base. However, conventional vector-based RAG delivers rapid responses but often returns contextually vague results, while knowledge graph (KG)-based methods offer structured relational reasoning at the expense of scalability and efficiency. To address these challenges, a hybrid KG-Vector RAG framework that systematically integrates structured KG metadata with unstructured vector retrieval is proposed. Firstly, a metadata-enriched KG was constructed from domain corpora by systematically extracting and indexing structured information to capture essential domain-specific relationships. Secondly, semantic alignment was achieved by injecting domain-specific constraints to refine and enhance the contextual relevance of the knowledge representations. Lastly, a layered hybrid retrieval strategy was employed that combined the explicit reasoning capabilities of the KG with the efficient search power of vector-based similarity methods, and the resulting outputs were integrated via prompt engineering to generate comprehensive, context-aware responses. Evaluated on design for additive manufacturing (DfAM) tasks, the proposed approach achieved 77.8% exact match accuracy and 76.5% context precision. This study establishes a new paradigm for industrial LLM systems, which demonstrates that hybrid symbolic-neural architectures can overcome the precision-scalability trade-off in mission-critical manufacturing applications. Experimental results indicated that integrating structured KG information with vector-based retrieval and prompt engineering can enhance retrieval accuracy, contextual relevance, and efficiency in LLM-based Q&A systems for SM.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Schools > Engineering
Publisher:	Elsevier
ISSN:	1474-0346
Funders:	National Natural Science Foundation of China
Date of First Compliant Deposit:	3 March 2025
Date of Acceptance:	13 March 2025
Last Modified:	06 Mar 2025 10:15
URI:	https://orca.cardiff.ac.uk/id/eprint/176569

Actions (repository staff only)

Edit Item