In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
App. Res. of Comp. Accepted Paper
Vol. 42, 2025 No. 10

Topic inference model based on retrieval augmented generation

Pan Lihu
Li Jie
Zhao Hongyan
College of Computer Science & Technology, Taiyuan University of Science & Technology, Taiyuan 030024, China
DOI: 10.19734/j.issn.1001-3695.2025.03.0059

Abstract

To address the challenges of insufficient topic diversity and limited model interpretability faced by large language models (LLMs) in topic modeling, this paper proposed a topic inference model based on Retrieval Augmented Generation (TIM_RAG) , which achieved topic generation and distribution inference through three-stage architecture. First, in the RAG retrieval phase, it designed a multi-dimensional document similarity retrieval method that filtered similar documents exhibiting both term-frequency relevance and deep semantic associations, thus enriching the topic information of individual documents and enhancing topic diversity. Second, in the RAG generation phase, it implemented a multi-perspective topic generation strategy, using chain-of-thought prompting to guide the LLM in extracting multi-angle topic terms and generating intermediate reasoning steps to increase process transparency. Finally, in the independent inference phase, it introduced an embedding transport plan based on optimal transport theory to model semantic relationships between document-topic and topic-word, significantly improving model interpretability. Experiments on the WikiText-103, BBC News, and 20 Newsgroups datasets show that TIM_RAG effectively mitigates topic diversity limitations while enhancing topic modeling performance.

Foundation Support

山西省自然科学面上基金项目(202203021211199)
山西省重点实验室开放基金项目(CICIP2022004)
太原科技大学博士科研启动基金资助项目(20212075)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.03.0059
Publish at: Application Research of Computers Accepted Paper, Vol. 42, 2025 No. 10

Publish History

[2025-06-19] Accepted Paper

Cite This Article

潘理虎, 李婕, 赵红燕. 基于检索增强生成的主题推理模型 [J]. 计算机应用研究, 2025, 42 (10). (2025-06-19). https://doi.org/10.19734/j.issn.1001-3695.2025.03.0059. (Pan Lihu, Li Jie, Zhao Hongyan. Topic inference model based on retrieval augmented generation [J]. Application Research of Computers, 2025, 42 (10). (2025-06-19). https://doi.org/10.19734/j.issn.1001-3695.2025.03.0059. )

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
  • 2020-2022 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)