App. Res. of Comp. Accepted Paper
Vol. 44, 2027 No. 2

Deep detection method for sensitive information in large language models based on retrieval-augmented generation and external knowledge fusion

Lin Qunxiong
Han Yuxing
Tsinghua Shenzhen International Graduate School, Shenzhen 518055, China
DOI: 10.19734/j.issn.1001-3695.2026.06.0171

Abstract

To address implicit semantic recognition difficulties, insufficient external knowledge support, and poor interpretability in sensitive information detection for large language models (LLMs) , this paper proposes a detection method based on retrieval-augmented generation (RAG) and external knowledge fusion. The method constructs a multi-source dynamic sensitive knowledge base from laws, industry standards, violation cases, and sensitive word graphs; designs an evidence-oriented RAG strategy combining fine-grained retrieval, multi-hop reasoning, noise filtering, and poisoning defense; and proposes an evidence-aware prompting mechanism that injects structured evidence into LLM reasoning, where LoRA fine-tuning upgrades detection from pattern matching to logical reasoning with traceable structured output. Experiments on four benchmark datasets show F1 scores of 88.76%–92.17%, significantly outperforming BM25, zero-shot LLMs, Naive RAG, and Graph RAG. These results indicate that fusing external knowledge with RAG effectively enhances recognition and interpretation of implicit sensitive semantics, offering a feasible path for LLM content safety governance.

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.06.0171
Publish at: Application Research of Computers Accepted Paper, Vol. 44, 2027 No. 2

Publish History

[2026-10-22] Accepted Paper

Cite This Article

林群雄, 韩宇星. 基于检索增强生成与外部知识融合的大模型敏感信息深度检测方法 [J]. 计算机应用研究, 2027, 44 (2). (2026-10-24). https://doi.org/10.19734/j.issn.1001-3695.2026.06.0171. (Lin Qunxiong, Han Yuxing. Deep detection method for sensitive information in large language models based on retrieval-augmented generation and external knowledge fusion [J]. Application Research of Computers, 2027, 44 (2). (2026-10-24). https://doi.org/10.19734/j.issn.1001-3695.2026.06.0171. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2025 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)