RESEARCH PAPERS

Research on the Application of Retrieval Augmented Thoughts in Library Knowledge Mining Services

  • Guo Limin ,
  • Fu Yaming ,
  • Liu Yueru
Expand
  • 1 Shanghai Library/Institute of Scientific & Technical Information of Shanghai, Shanghai 200031;
    2 School of Cultural Heritage and Information Management, Shanghai University, Shanghai 200444;
    3 Tongji University Library, Shanghai 200092
Guo Limin, Associate Research Librarian, Master’s Degree; Fu Yaming, Assistant Researcher, PhD, Corresponding Author, E-mail: ymingfu@126.com; Liu Yueru, Associate Research Librarian, Master’s Degree.

Received date: 2024-10-15

  Revised date: 2024-12-17

  Online published: 2025-11-11

Supported by

This work is supported by Shanghai Magnolia Talent Program Pujiang Project titled “Research on Cultural Heritage Knowledge Service Based on Generative Artificial Intelligence”(Grant No. 24PJC036);the Philosophy and Social Sciences of Shanghai Project titled “Smart DataDriven Research Innovation Support Services in Metropolitan Libraries”(Grant No. 2020BTQ005).

Abstract

[Purpose/Significance] The study focuses on the development of library knowledge mining services in the era of large language models. It explores the integration of traditional retrieval methods with retrieval augmented thoughts(RAT) to provide users with both profound and logically rigorous knowledge information, aiming to enhance the quality of library knowledge services. [Method/Process] The study adopted an experimental research approach, taking the Name Authority Database of Shanghai Library as the data source. It specifically focused on mining information related to tea culture in Song Dynasty, uncovering more details about this historical period from library collections, thus offering users a more comprehensive and in-depth perspective. [Result/Conclusion] Experimental results indicate that the RAT method has certain advantages in library knowledge mining services. This approach not only improves the efficiency and accuracy of data mining but also provides new technical solutions for library knowledge mining, offering valuable insights for the development of smart libraries.

Cite this article

Guo Limin , Fu Yaming , Liu Yueru . Research on the Application of Retrieval Augmented Thoughts in Library Knowledge Mining Services[J]. Library and Information Service, 2025 , 69(21) : 108 -119 . DOI: 10.13266/j.issn.0252-3116.2025.21.009

References

[1] PAN Y. Heading toward artificial intelligence 2.0[J]. Engineering,2016, 2(4):409-413.
[2] 郭利敏,付雅明.融合ReAct模式的图书馆大语言模型知识服务系统构建[J].图书馆论坛, 2024, 44(6):61-70.(GUO L M,FU Y M. An LLM-based knowledge service system for libraries integrating the ReAct model[J]. Library tribune, 2024, 44(6):61-70.)
[3] ZHUANG Y, WU F, CHEN C, et al. Challenges and opportunities:from big data to knowledge in AI 2.0[J]. Frontiers of information technology&electronic engineering, 2017, 18:3-14.
[4] 张晓林.颠覆性变革与后图书馆时代--推动知识服务的供给侧结构性改革[J].中国图书馆学报, 2018, 44(1):4-16.(ZHANG X L. Disruptive changes and the post-library era:toward supply-side structure reform of knowledge services[J].Journal of library science in China, 2018, 44(1):4-16.)
[5] 左静远.基于知识挖掘技术的公共图书馆智慧服务调查与思考[J].情报探索, 2023(9):100-107.(ZUO J Y. Investigation and reflection on intelligent service of public library based on knowledge mining technology[J]. Information research, 2023(9):100-107.)
[6] 陈帅朴,刘芳霖,钱宇星,等.检入新境:大语言模型引领的信息检索主题与知识关联演化分析[J].图书情报知识,2025, 42(3):53-65, 87.(CHEN S P, LIU F L, QIAN Y X, et al.Topic and knowledge association evolution in the field of large language model-enabled information retrieval[J]. Documentation,information&knowledge, 2025, 42(3):53-65, 87.)
[7] 张宏玲,沈立力,韩春磊,等.大语言模型对图书馆数字人文工作的挑战及应对思考[J].图书馆杂志, 2023, 42(11):31-39, 61.(HONG L Z, SHEN L L, HAN C L, et al. Challenges and reflections on the practical application of large language model in digital humanities work at libraries[J]. Library journal, 2023,42(11):31-39, 61.)
[8] WANG Z, LIU A, LIN H, et al. Rat:retrieval augmented thoughts elicit context-aware reasoning in long-horizon generation[EB/OL].[2025-03-17]. https://arxiv.org/abs/2403.05313.
[9] 王颖纯,董雪敏,刘燕权.基于知识挖掘的图书馆智慧推荐服务模式[J].图书馆学研究, 2018(9):37-43.(WANG C Y,DONG X M, LIU Y Q. Service mode of smart recommendation based on knowledge mining[J]. Research on library science,2018(9):37-43.)
[10] 张晓林.重新认识知识过程和知识服务[J].图书情报工作,2009, 53(1):6-8.(ZHANG X L. Reconceiving the knowledge process and knowledge service[J]. Library and information service, 2009, 53(1):6-8.)
[11] 温有奎,温浩,乔晓东.让知识产生智慧--基于人工智能的文本挖掘与问答技术研究[J].情报学报, 2019, 38(7):722-730.(WEN Y K, WEN H, QIAO X D. Research on the methods of information Science and artificial intelligence fusion innovation[J]. Journal of the China Society for Scientific and Technical Information, 2019, 38(7):722-730.)
[12] 罗威,谭玉珊.基于内容的科技文献大数据挖掘与应用[J].情报理论与实践, 2021, 44(6):154-157.(LUO W, TAN Y S.Content-based data mining and application of scientific and technical literature big data[J]. Information studies:theory&application, 2021, 44(6):154-157.)
[13] 王露莹.大数据时代图书馆馆藏资源的知识标注与知识挖掘研究[J].农业图书情报学刊, 2018, 30(10):70-73.(WANG L Y. Research on knowledge annotation and mining of library collection resource in the era of big data[J]. Journal of library and information science in agriculture, 2018, 30(10):70-73.)
[14] 胡昊天,邓三鸿,孔玲,等.生成式情报学术语自动抽取与多维关联知识挖掘研究[J].情报学报, 2024, 43(5):588-600.(WANG L Y, DENG S H, KONG L, et al. Automatic generative information science term extraction and multidimensional linked knowledge mining[J]. Journal of the China Society for Scientific and Technical Information, 2024, 43(5):588-600.)
[15] BERTI A, QAFARI M S. Leveraging large language models (llms) for process mining (technical report)[EB/OL].[2025-03-17]. https://arxiv.org/abs/2307.12701.
[16] JOSÉC D J, RACHEL H, RICHARD S, et al. Domaindriven LLM development:insights into RAG and fine-tuning practices[C]//Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining (KDD'24). New York:Association for Computing Machinery, 2024:6416-6417.
[17] WAN M, SAFAVI T, JAUHAR S K, et al. TNT-LLM:text mining at scale with large language models[C]//Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining. New York:Association for Computing Machinery,2024:5836-5847.
[18] UZUNOGLU A, SAFA A R,ŞAHIN G G. Paradise:evaluating implicit planning skills of language models with procedural warnings and tips datase[EB/OL].[2025-03-17]. https://arxiv.org/abs/2403.03167.
[19] ZHANG Z, FANG M, CHEN L, et al. How do large language models capture the ever-changing world knowledge?a review of recent advances[EB/OL].[2025-03-17]. https://arxiv.org/abs/2310.07343.
[20] 黄永文,孙坦,赵瑞雪,等.大数据与人工智能背景下新型知识服务研究与实践[J].图书情报工作, 2022, 66(19):36-46.(HUANG Y W, SUN T, ZHAO R X, et al. Research and practice of new knowledge service in the context of big data and artificial intelligence[J]. Library and information service, 2022, 66(19):36-46.)
[21] 赵月,何锦雯,朱申辰,等.大语言模型安全现状与挑战[J].计算机科学, 2024, 51(1):68-71.(ZHAO Y, HE J W, ZHU S C, et al. Security of large language models:current status and challenges[J]. Computer science, 2024, 51(1):68-71.)
[22] LEWIS P, PEREZ E, PIKTUS A, et al. Retrieval-augmented generation for knowledge-intensive nlp tasks[J]. Advances in neural information processing systems, 2020, 33:9459-9474.
[23] YU H, GAN A, ZHANG K, et al. Evaluation of retrieval-augmented generation:a survey[C]//CCF conference on big data.Singapore:Springer Nature, 2024:102-120.
[24] WEI J, WANG X, SCHUURMANS D, et al. Chain-of-thought prompting elicits reasoning in large language models[J].Advances in neural information processing systems, 2022, 35:24824-24837.
[25] CHU Z, CHEN J, CHEN Q, et al. Navigate through enigmatic labyrinth a survey of chain of thought reasoning:advances,frontiers and future[EB/OL].[2025-03-17]. https://arxiv.org/abs/2309.15402.
[26] 邓盼盼,李军莲,冀玉静,等. NSTL科技文献资源分类体系构建研究[J].数字图书馆论坛, 2024, 20(8):1-8.(DENG P P, LI J L, JI Y J, et al. Construction of NSTL scientific and technological literature resource classification system[J]. Digital library forum, 2024, 20(8):1-8.)
[27] 夏毅,兰明敬,陈晓慧,等.可解释的知识图谱推理方法综述[J].网络与信息安全学报, 2022, 8(5):1-25.(XIA Y,LAN M J, CHEN X H, et al. Survey on explainable knowledge graph reasoning methods[J]. Chinese journal of network and information security, 2022, 8(5):1-25.)
[28] 王娟,曹树金,王志红,等.面向探索式搜索的领域知识图谱构建及实验探索[J].图书情报工作, 2024, 68(3):105-116.(WANG J, CAO S J, WANG Z H, et al. Construction and experimental exploration of domain knowledge graph for exploratory search[J]. Library and information service, 2024,68(3):105-116.)
[29] 田杰,周军兰.智慧图书馆模型与系统体系构建探析[J].文献与数据学报, 2020, 2(2):40-48.(TIAN J, ZHOU J L.A study on the construction of smart library model and system[J]. Journal of library and data, 2020, 2(2):40-48.)
Outlines

/

〈 〉