Large Language Model-Driven Construction of the Yuhua Martyrs Knowledge Graph

He Lin; Tian Xinyu

doi:10.13266/j.issn.0252-3116.2026.02.003

Library and Information Service >

2026 , Vol. 70 >Issue 2: 27 - 40

DOI: https://doi.org/10.13266/j.issn.0252-3116.2026.02.003

SPECIAL TOPIC: Knowledge Organization and Utilization of Red Literature

Large Language Model-Driven Construction of the Yuhua Martyrs Knowledge Graph

He Lin ,
Tian Xinyu

Expand

1 College of Information Management, Nanjing Agricultural University, Nanjing 210095;
2 Library of Nanjing Agricultural University, Nanjing 210095

He Lin, Professor, Doctoral Supervisor, E-mail: helin@njau.edu.cn;Tian Xinyu, Master’s Candidate.

Received date: 2025-05-07

Revised date: 2025-08-27

Online published: 2026-01-21

Fold

Abstract

[Purpose/Significance] This study applies large language models to construct the Yuhua Martyrs knowledge graph. It aims to organize knowledge from low-resource textual data and provide a methodological reference for expanding the application of historical revolutionary materials, such as Yuhua Martyrs’ literature. [Method/Process] During the knowledge extraction phase, domain-specific instruction templates were designed for different tasks. The Chinese-Llama2 model was fine-tuned on a small annotated dataset. GPT-4 served as the baseline model, with GLM-4 and Llama3 as experimental models, to systematically evaluate the performance of unsupervised large language models versus fine-tuned models in structured knowledge extraction. The optimized knowledge extraction framework was applied to construct a high-quality knowledge graph. [Result/Conclusion] Leveraging large language models for Yuhua Martyrs knowledge graph construction significantly enhances knowledge acquisition efficiency for low-annotation text resources. It establishes a replicable technical framework for knowledge engineering in similar red literature.

Key words： large language model; knowledge graph; Yuhua Martyrs; red literature

Cite this article

He Lin , Tian Xinyu . Large Language Model-Driven Construction of the Yuhua Martyrs Knowledge Graph[J]. Library and Information Service, 2026 , 70(2) : 27 -40 . DOI: 10.13266/j.issn.0252-3116.2026.02.003

References

[1] 徐建华, 杨丽娟, 伍巧. 图书馆红色文献与红色专藏[J]. 图书馆论坛, 2021, 41(7):40-45. (XU J H, YANG L J, WU Q. Red literature and red special collection in libraries[J]. Library tribune, 2021, 41(7):40-45.)
[2] 刘倩倩, 夏翠娟, 朱武信. 红色文化传承视域下的红色文献服务平台建设实践与思考[J]. 信息资源管理学报, 2021,11(4):17-24. (LIU Q Q, XIA C J, ZHU W X. Construction and reflection of revolution (red) document service platform for the inheriting and spreading of red culture[J]. Journal of information resources management, 2021, 11(4):17-24.)
[3] 杨柳, 郑凯利. 雨花英烈红色家书融入党性教育工作探索思考[J]. 文物鉴定与鉴赏, 2025(1):99-103. (YANG L, ZHENG K L. Exploration and reflection on integrating Yuhua martyrs' red letters into party spirit education[J]. Identification and appreciation of cultural relics, 2025(1):99-103.)
[4] 房亚萍, 朱冰, 莫佳思. 雨花英烈近亲属口述档案在访谈式教学中的开发应用研究——以南京雨花台干部学院《感悟雨花魂传承英烈志》互动访谈课程为例[J]. 档案与建设, 2024(10):88-95. (FANG Y P, ZHU B, MO J S. Research on the development and application of oral archives from relatives of Yuhua martyrs in interview-based teaching:taking the interactive interview class of "feeling the soul of Yuhua and inheriting the aspiration of martyrs" in Yuhuatai Cadre Institute as an example[J]. Archives & construction, 2024(10):88-95.)
[5] 中国国家图书馆. 中国历史文献总库· 红色文献数据库[EB/OL].[2025-07-15]. http://red.nlcpress.com/library/publish/default/Login.jsp. (National Library of China. China historical literature database:red literature collection[EB/OL].[2025- 07-15]. http://red.nlcpress.com/library/publish/default/Login.jsp.)
[6] 上海图书馆. 上海革命(红色) 文献服务平台[EB/OL].[2025-07-15]. https://red.library.sh.cn/index. (Shanghai Library. Shanghai revolutionary (red) literature service platform[EB/OL].[2025-07-15]. https://red.library.sh.cn/index.)
[7] 沈思佳. 强化数字化赋能,管好用好红色资源[EB/OL].[2025-09-10]. https://xh.xhby.net/pc/con/202312/19/content_1277065.html (Shen Sijia. Strengthening digital empowerment to better manage and utilize red resources[EB/OL].[2025- 09-10]. https://xh.xhby.net/pc/con/202312/19/content_1277065.html)
[8] 刘维荣, 蒋毓娴. 春应有时莫辜负——雨花女英烈张应春传奇[J]. 档案天地, 2023(3):10-12, 53. (LIU W R, JING Y X. Spring should be cherished:the legend of Zhang Yingchun, a female martyr of Yuhua[J]. Archives world, 2023(3):10-12, 53.)
[9] 刘维荣, 许永涛. 讲好新四军中的雨花英烈故事[J]. 唯实, 2024(8):93-96. (LIU W R, XU Y T. Telling the Stories of Yuhua martyrs in the New fourth army[J]. Reality only, 2024(8):93- 96.)
[10] 谭志云, 何淼. 新时代红色文化的社会化传播探索——以雨花英烈精神为例[J]. 文化产业研究, 2023(1):264-273. (TAN Z Y, HE M. Exploration on socialized communication of red culture in the new era:taking the spirit of the Yuhua martyrs as an example[J]. Cultural industry research, 2023(1):264-273.)
[11] 赵杨娟, 莫佳思. 雨花英烈革命精神的历史成因、鲜明特征及传承路径[J]. 中共南京市委党校学报, 2022(6):33-38. (ZHAO Y J, MO J S. The historical cause and distinctive characteristics of the Yuhua heroic revolutionary spirit[J]. Journal of the Party School of Nanjing Municipal Committee of the CPC, 2022(6):33-38.)
[12] 赵杨娟, 郑凯利, 马宏瑞. 红色基因传承视阈下雨花英烈红色档案叙事化开发策略研究[J]. 档案与建设, 2024(6):71-77. (ZHAO Y J, ZHENG K L, MA H R. Research on the narrative development strategy of the red archives of Yuhua martyrs from the perspective of red gene inheritance[J]. Archives & construction, 2024(6):71-77.)
[13] 赵浜, 曹树金. 国内外生成式AI 大模型执行情报领域典型任务的测试分析[J]. 情报资料工作, 2023, 44(5):6-17. (ZHAO B, CAO S J. Test analysis of typical tasks in the information field performed by generative AI large models at home and abroad[J]. Information and documentation services, 2023, 44(5):6-17.)
[14] HAN R, PENG T, YANG C, et al. Is information extraction solved by ChatGPT? An analysis of performance, evaluation criteria, robustness and errors[J]. arXiv preprint arXiv:2305.14450, 2023:48.
[15] QIN C, ZHANG A, ZHANG Z, et al. Is ChatGPT a general-purpose natural language processing task solver?[J]. arXiv preprint arXiv:2302.06476, 2023.
[16] AMIN M M, CAMBRIA E, SCHULLER B W. Will affective computing emerge from foundation models and general artificial intelligence? A first evaluation of ChatGPT[J]. IEEE intelligent systems, 2023, 38(2):15-23.
[17] POLAK M P, MORGAN D. Extracting accurate materials data from research papers with conversational language models and prompt engineering[J]. Nature communications, 2024, 15(1):1569.
[18] ZANDVOORT D, WIERSEMA L, HUIBERS T, et al. Enhancing summarization performance through transformer-based prompt engineering in automated medical reporting[J]. arXiv preprint arXiv:2311.13274, 2023.
[19] 陆伟, 汪磊, 程齐凯, 等. 数智赋能信息资源管理新路径:指令工程的概念、内涵和发展[J]. 图书情报知识, 2024, 41(1):6-11. (LU W, WANG L, CHENG Q K, et al. A new approach for information resources management empowered by data intelligence:the concept, connotation and development of instruction engineering[J]. Documentation, information & knowledge, 2024, 41(1):6-11.)
[20] 斯日古楞, 林民, 郭振东, 等. 基于提示学习和抽取式阅读理解的古籍礼仪实体关系联合抽取方法研究[J]. 数据分析与知识发现, 2025, 9(3):147-159. (SIRIGULENG, LIN M, GUO Z D,et al. Etiquette Entity-relation extraction via prompt learning and extractive reading comprehension[J]. Data analysis and knowledge discovery, 2025, 9(3):147-159.)
[21] DAGDELEN J, DUNN A, LEE S, et al. Structured information extraction from scientific text with large language models[J]. Nature communications, 2024, 15(1):1418.
[22] 段宇锋, 谢佳宏. 基于大语言模型和提示工程的中文医学文本实体关系抽取研究[J]. 数据分析与知识发现, 2025, 9(9):25-36. (DUAN Y F, XIE J H. Entity relation extraction of Chinese medical text based on large language model and prompt engineering[J]. Data analysis and knowledge discovery, 2025, 9(9):25-36.)
[23] WADHWA S, AMIR S, WALLACE B C. Revisiting relation extraction in the era of large language models[C]//Proceedings of the 61st annual meeting of the Association for Computational Linguistics. Toronto:Association for Computational Linguistics, 2023:15566.
[24] ZHANG K, GUTIERREZ B J, SU Y. Aligning instruction tasks unlocks large language models as zero-shot relation extractors[C]//The 61st annual meeting of the Association for Computational Linguistics. Toronto:Association for Computational Linguistics, 2023:794-812.
[25] 何琳, 武帅, 叶雅慧, 等. 基于轻量级本体的雨花英烈群体特征构建与分析研究[J]. 农业图书情报学报, 2022, 34(12):33- 44. (HE L, WU S, YE Y H, et al. Analysis of the group characteristics of Yuhua heroes based on lightweight ontology[J]. Journal of library and information science in agriculture, 2022, 34(12):33-44.)
[26] 武帅, 何琳, 杨海龄, 等. 迁移学习视角下红色文献元数据表示体系构建探究[J]. 情报资料工作, 2024, 45(6):84-92. (WU S, HE L, YANG H L, et al. A Probe into the construction of red literature metadata representation system from the perspective of transfer learning[J]. Information and documentation services, 2024, 45(6):84-92.)

Options

Outlines

模态框（Modal）标题

Abstract

Cite this article

References