Academic Journal of Computing & Information Science, 2026, 9(9); doi: 10.25236/AJCIS.2026.090906.
Linglong Mao, Shuang Wang
School of Electronic Engineering, Tianjin University of Technology and Education, Tianjin, 300222, China
To improve technical-document retrieval and knowledge reuse in chip testing enterprises, this study develops a retrieval-augmented generation (RAG) knowledge base. Chip models and test-equipment names are linked with document segments, and dense-sparse hybrid retrieval is combined with HyDE query expansion, chip-model/equipment-name filtering, and knowledge-graph retrieval. Experiments on five technical documents and 40 question-answer pairs show that HyDE improves relevant-content recall and name filtering strengthens consistency between answers and source documents, while the effect of knowledge-graph retrieval varies with document structure and question type. The system provides a practical approach to technical-document retrieval in chip testing enterprises.
chip testing enterprises; knowledge management; retrieval-augmented generation; hybrid retrieval; knowledge graph
Linglong Mao, Shuang Wang. Design and Optimization of a RAG Knowledge Base for Knowledge Management in Chip Testing Enterprises. Academic Journal of Computing & Information Science (2026), Vol. 9, Issue 9: 40-46. https://doi.org/10.25236/AJCIS.2026.090906.
[1] Lewis P, Perez E, Piktus A, et al. Retrieval-augmented generation for knowledge-intensive NLP tasks[C]//Advances in Neural Information Processing Systems 33. 2020: 9459-9474.
[2] Gao L, Ma X, Lin J, et al. Precise zero-shot dense retrieval without relevance labels[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023: 1762-1777.
[3] Chen J, Xiao S, Zhang P, et al. M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation[C]//Findings of the Association for Computational Linguistics: ACL 2024. Bangkok: Association for Computational Linguistics, 2024: 2318-2335. DOI: 10.18653/v1/2024.findings-acl.137.
[4] Cormack G V, Clarke C L A, Büttcher S. Reciprocal rank fusion outperforms Condorcet and individual rank learning methods[C]//Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2009: 758-759.
[5] Nogueira R, Cho K. Passage re-ranking with BERT[EB/OL]. (2019-01-13). https://arxiv.org/abs/1901.04085.
[6] Edge D, Trinh H, Cheng N, et al. From local to global: A graph RAG approach to query-focused summarization[EB/OL]. (2024-04-24). https://arxiv.org/abs/2404.16130.
[7] Es S, James J, Espinosa-Anke L, et al. RAGAs: Automated evaluation of retrieval augmented generation[C]//Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations. 2024: 150-158.
[8] Wang J, Yi X, Guo R, et al. Milvus: A purpose-built vector data management system[C]//Proceedings of the 2021 International Conference on Management of Data. 2021: 2614-2627.
[9] Wang B, Xu C, Zhao X, et al. MinerU: An open-source solution for precise document content extraction[EB/OL]. (2024-09-27). https://arxiv.org/abs/2409.18839.
[10] Ni B, Liu Z, Wang L, et al. Towards trustworthy retrieval augmented generation for large language models: A survey[EB/OL]. (2025-02-08). https://arxiv.org/abs/2502.06872.
[11] Gan A, Yu H, Zhang K, et al. Retrieval augmented generation evaluation in the era of large language models: A comprehensive survey[EB/OL]. (2025-04-21). https://arxiv.org/abs/2504.14891.
[12] Li Y, Zhang W, Yang Y, et al. A survey of RAG-reasoning systems in large language models[C]//Findings of the Association for Computational Linguistics: EMNLP 2025. Suzhou: Association for Computational Linguistics, 2025: 12120-12145. DOI: 10.18653/v1/2025.findings-emnlp.648.