Automatic Identification and Quantitative Analysis of Pre-Qin Philosophers’ Texts Cited in The Twenty-Four Histories

Hu Die; Zhao Wenhua; Wang Xiyu; Liu Liu

doi:10.13266/j.issn.0252-3116.2026.05.004

Library and Information Service >

2026 , Vol. 70 >Issue 5: 41 - 55

DOI: https://doi.org/10.13266/j.issn.0252-3116.2026.05.004

RESEARCH PAPERS

Automatic Identification and Quantitative Analysis of Pre-Qin Philosophers’ Texts Cited in The Twenty-Four Histories

Hu Die ,
Zhao Wenhua ,
Wang Xiyu ,
Liu Liu

Expand

1 School of Information Resource Management, Renmin University of China, Beijing 100872;
2 College of Information Management, Nanjing Agricultural University, Nanjing 210095;
3 Research Center for Humanities and Social Computing, Nanjing Agricultural University, Nanjing 210095

Hu Die, Doctoral Candidate; Zhao Wenhua, Master’s Candidate; Wang Xiyu, Master’s Candidate; Liu Liu, Associate Professor, PhD, Master’s Supervisor, Corresponding Author, E-mail: liuliu@njau.edu.cn.

Received date: 2025-01-03

Revised date: 2025-02-19

Online published: 2026-03-04

Supported by

This work is supported by the National Social Science Fund of China project titled “Construction of Knowledge Base for Pre-Qin Philosophers’ Texts and Dictionary Compilation” (Grant No.22&ZD262) and the Social Science Foundation of Jiangsu Province project titled “Research on the Construction and Application of Knowledge Graphs in the Twenty-Four Histories” (Grant No.24TQB004).

Fold

Abstract

[Purpose/Significance] The Twenty-Four Histories, as an important compilation of officially revised histories in ancient China, frequently quotes from the classics of pre-Qin philosophers. Systematically reviewing and analyzing these citations is of great significance for revealing the inheritance and evolution of the philosophers’ thought. This study aims to construct a word-level book citation identification framework to achieve fine-grained identification and analysis of pre-Qin philosophers’ citations in historical records. This will provide a reliable method for identifying book citations in the study of classical Chinese texts and open up a new analytical perspective for the study of pre-Qin philosophers. [Method/Process] Firstly, an unsupervised ancient Chinese retrieval model was selected to assist imanual annotation, establish a preliminary corpus of pre-Qin philosophers’ citations in The Twenty-Four Histories. Secondly, based on the annotated corpus, a fine-grained citation identification model is developed using a large language model–based retrieval-augmented generation framework. A human-computer collaborative iterative strategy was adopted to improve the book citation corpus and optimize model performance. Finally, a multidimensional quantitative analysis of pre-Qin philosophers’ citations in historical records was conducted. [Result/Conclusion] When the retriever returns the top three sentences with the highest similarity, using Esimcse-GujiRoBERTa_ts as the ancient Chinese text retriever and the fine-tuned internlm2_5-7b-chat as the text generator, the constructed book citation identification framework achieves an F1 score of 98.59% in judging whether a text contains book citations and an F1 score of 82.65% in sequence annotation for text output. Subsequent quantitative analysis confirms the important status of Confucianism, represented by The Analects, across different historical periods.

Key words： fine-grained ancient book citation identification; LLMs retrieval-augmented generation; works of pre-Qin philosophers; Twenty-Four Histories

Cite this article

Hu Die , Zhao Wenhua , Wang Xiyu , Liu Liu . Automatic Identification and Quantitative Analysis of Pre-Qin Philosophers’ Texts Cited in The Twenty-Four Histories[J]. Library and Information Service, 2026 , 70(5) : 41 -55 . DOI: 10.13266/j.issn.0252-3116.2026.05.004

References

[1] 黄水清, 周好, 彭秋茹, 等. 引书的自动识别及文献计量学分析[J]. 情报学报, 2021, 40(12): 1325-1337. (HUANG S Q, ZHOU H, PENG Q R, et al. Automatic recognition and bibliometric analysis of cited books[J]. Journal of the China Society for Scientific and Technical Information, 2021, 40(12): 1325-1337.)
[2] 黄水清, 刘浏, 王东波. 计算人文学科的内涵、体系及机遇[J]. 图书与情报, 2023, 43(1): 1-11. (HUANG S Q, LIU L, WANG D B. The connotation, system and opportunity of computational humanities[J]. Library and information, 2023, 43(1): 1-11.)
[3] 刘浏, 齐月, 刘雏菲, 等. 计算人文下的古籍引书研究及全文本知识库的构建[J]. 情报学报, 2023, 42(12): 1498-1512. (LIU L, QI Y, LIU C F, et al. Research on ancient book citations from the perspective of computational humanities and the construction of full-text knowledge base[J]. Journal of the China Society for Scientific and Technical Information, 2023, 42(12): 1498-1512.)
[4] 张海, 赵雪, 王东波. 大语言模型下古籍智能信息处理：构成要素、框架体系与实践路径研究[J]. 信息资源管理学报, 2024, 14(5): 36-44. (ZHANG H, ZHAO X, WANG D B. Research on intelligent information processing of ancient books under the large language model: constituent elements, framework system, and practical path[J]. Journal of information resources management, 2024, 14(5): 36-44.)
[5] 岳宗伟. 《论衡》引书研究[D]. 上海: 复旦大学, 2007. (YUE Z W. A study of citations in the Lunheng[D]. Shanghai: Fudan University, 2007.)
[6] 熊桂芬. 从引书看《广韵》的文献学价值[J]. 中国典籍与文化, 2006(1): 35-40. (XIONG G F. The philological value of Guangyun as seen through its citations[J]. Chinese classics and culture, 2006(1): 35-40.)
[7] 吴泽顺. 《史记》引书异文释例[J]. 古籍整理研究学刊, 1993(4): 24-27. (WU Z S. An explanation of variant readings in the citations of Shiji[J]. Journal of ancient books collation and studies, 1993(4): 24-27.)
[8] 梁媛, 王东波, 黄水清. 古籍同事异文的自动发掘研究[J]. 图书情报工作, 2021, 65(9): 97-104. (LIANG Y, WANG D B, HUANG S Q. Research on automatic mining of variants expressing the same event in the ancient books[J]. Library and information service, 2021, 65(9): 97-104.)
[9] LI W, SHAO Y, BI M. data construction and matching method for the task of ancient classics reference detection[C]//Proceedings of the 21st Chinese National Conference on Computational Linguistics. Nanchang: Chinese Information Processing Society of China, 2022: 600-610.
[10] DUAN S, WANG J, YANG H, et al. Disentangling the cultural evolution of ancient China: a digital humanities perspective[J]. Humanities and social sciences communications, 2023, 10(1): 310.
[11] GUPTA S, RANJAN R, SINGH S N. A comprehensive survey of retrieval-augmented generation (RAG): evolution, current landscape and future directions[EB/OL]. [2025-02-18]. https://arxiv.org/abs/2410.12837.
[12] HUANG L, YU W, MA W, et al. A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions[J]. ACM transactions on information systems, 2025, 43(2): 1-55.
[13] ZHU Y, YUAN H, WANG S, et al. Large language models for information retrieval: a survey[EB/OL]. [2025-02-18]. https://arxiv.org/abs/2308.07107.
[14] PARVEZ M R, AHMAD W U, CHAKRABORTY S, et al. Retrieval augmented code generation and summarization[EB/OL]. [2025-02-18]. https://arxiv.org/abs/2108.11601.
[15] BALAGUER A, BENARA V, DE FREITAS CUNHA R L, et al. RAG vs fine-tuning: pipelines, tradeoffs, and a case study on agriculture[EB/OL]. [2025-02-18]. https://arxiv.org/abs/2401.08406.
[16] ZHAO S, CHEN S, ZHOU J, et al. Potential to transform words to watts with large language models in battery research[J]. Cell reports physical science, 2024, 5(3): 1-12.
[17] KOIZUMI Y, OHISHI Y, NIIZUMI D, et al. Audio captioning using pre-trained large-scale language model guided by audio-based similar caption retrieval[EB/OL]. [2025-02-18]. https://arxiv.org/abs/2012.07331.
[18] JIN Q, YANG Y, CHEN Q, et al. Genegpt: augmenting large language models with domain tools for improved access to biomedical information[J]. Bioinformatics, 2024, 40(2): btae075.
[19] GUO X, PATKI R, EVERAERT D, et al. Retrieval augmented spelling correction for E-Commerce applications[EB/OL]. [2025-02-18]. https://arxiv.org/abs/2410.11655.
[20] 张晓冰, 张佩. 古籍数字化出版的挑战与发展路径研究——以“识典古籍”为例[J]. 北京印刷学院学报, 2024, 32(9): 1-6. (ZHANG X B, ZHANG P. Research on the challenges and development paths of digital publishing of ancient books: taking “Shi-dian Ancient Books” as an example[J]. Journal of Beijing Institute of Graphic Communication, 2024, 32(9): 1-6.)
[21] 孟序阳, 王昊, 李远清, 等. 基于细粒度知识图谱检索增强生成的提示学习研究[J]. 数据分析与知识发现, 2025, 9(9): 1-12. (MENG X Y, WANG H, LI Y Q, et al. Prompt learning based on retrieval-augmented generation with fine-grained knowledge graph[J]. Data analysis and knowledge discovery, 2025, 9(9): 1-12.)
[22] 王文. 韩愈、柳宗元引用先秦诸子文献研究[D]. 武汉: 华中师范大学, 2020. (WANG W. Research on Han Yu, Liu Zongyuan Quoting Literature from pre-Qin Dynasty[D]. Wuhan: Central China Normal University, 2020.)
[23] 王东波, 何琳, 黄水清. 基于支持向量机的先秦诸子典籍自动分类研究[J]. 图书情报工作, 2017(12): 71-76. (WANG D B, HE L, HUANG S Q. Research of automatic classification for Pre-Qin philosophers literature based on the support vector machine[J]. Library and information service, 2017(12): 71-76.)
[24] 子润先生. 《汉书·艺文志》现存书目梳理（二）诸子略[EB/OL]. [2025-02-18]. https://zhuanlan.zhihu.com/p/378684644. (Mr. ZIRUN. A list of existing books in Han Shu: Bibliography of Arts and Literature (II): a brief overview of philosophers[EB/OL]. [2025-02-18]. https://zhuanlan.zhihu.com/p/378684644.)
[25] 李零. 简帛古书与学术源流：修订本[M]. 北京: 生活·读书·新知三联书店, 2008. (LI L. Bamboo slips and silk manuscripts in academic lineage: revised edition[M]. Beijing: Life, Reading, and New Knowledge Sanlian Bookstore, 2008.)
[26] 秦燕南. 《子思子》研究[D]. 郑州: 郑州大学, 2006. (QIN Y N. A study of Zisi Zi[D]. Zhengzhou: Zhengzhou University, 2006.)
[27] 李健胜. 辑佚本《子思子》考释[J]. 淮阴师范学院学报（哲学社会科学版）, 2010, 32(3): 333-337, 419. (LI J S. A study on the lost edition of Zisi Zi[J]. Journal of Huaiyin Teachers College (Social and Sciences Edition), 2010, 32(3): 333-337, 419.)
[28] STURGEON D. 中国哲学书电子化计划[EB/OL]. [2025-02-18]. https://ctext.org/zhs. (Sturgeon D. Chinese Text Project [EB/OL]. [2025-02-18]. https://ctext.org/zhs.)
[29] 国学大师网. 国学大师网[EB/OL]. [2025-02-10]. https://www.guoxuedashi.com. (Guoxue dashi website. guoxue dashi website [EB/OL]. [2025-02-10]. https://www.guoxuedashi.com.)
[30] 张晓明. 从《晋书》看《世说新语》对史传文学的贡献[D]. 北京: 首都师范大学, 2006. (ZHANG X M. The contribution of Shishuo Xinyu to historiographical literature as seen through Jin Shu[D]. Beijing: Capital Normal University, 2006.)
[31] 柳士镇. 《世说新语》《晋书》异文语言比较研究[J]. 中州学刊, 1988(6): 99-102, 49. (LIU S Z. A comparative study of variant readings in Shishuo Xinyu and Jin Shu[J]. Academic journal of Zhongzhou, 1988(6): 99-102, 49.)
[32] 刘畅, 王东波, 胡昊天, 等. 面向数字人文的融合外部特征的典籍自动分词研究——以SikuBERT预训练模型为例[J]. 图书馆论坛, 2022, 42(6): 44-54. (LIU C, WANG D B, HU H T, et al. Automatic word segmentation of classic books with external features for digital humanities：a case study of SikuBERT pre-training model[J]. Library Tribune, 2022, 42(6): 44-54.)
[33] WANG D, LIU C, ZHAO Z, et al. Gujibert and gujigpt: Construction of intelligent information processing foundation language models for ancient texts[EB/OL]. [2025-02-18]. https://arxiv.org/abs/2307.05354.
[34] 叶文豪, 胡蝶, 王东波, 等. 基于古籍大模型的无监督互文自动发现研究[J]. 图书情报工作, 2024, 68(23): 41-51. (YE W H, HU D, WANG D B, et al. Research on unsupervised automatic intertextual discovery based on large models of ancient books[J]. Library and Information Service, 2024, 68(23): 41-51.)
[35] 张亲霞. 先秦儒家君权思想的历史演变[D]. 西安: 陕西师范大学, 2005. (ZHANG Q X. The evolvement of Confucian regality ideas in pre-Qin dynasty[D]. Xi’an: Shaanxi Normal University, 2005.)
[36] 邢丽芳. 儒家教化及其有效性研究[D]. 天津: 南开大学, 2014. (XING L F. A Study of Confucian cultivation and Its Effectiveness[D]. Tianjin: Nankai University, 2014.)
[37] 陈庆魁. 论儒家思想成为封建统治思想的原因及影响[J]. 郑州航空工业管理学院学报（社会科学版）, 2011, 30(1): 68-70. (CHEN Q K. On the reasons and influences of Confucianism becoming the dominant ideology of feudal rule[J]. Journal of Zhengzhou University of Aeronautics (social science edition), 2011, 30(1): 68-70.)
[38] 姜晓娟, 蒋蔚. 论《史记》论赞对法家的评价[J]. 西南科技大学学报（哲学社会科学版）, 2018, 35(4): 6-13. (JIANG X J, JIANG W. Discussion on the comments of the historical records on legalists[J]. Journal of Southwest University of Science and Technology (philosophy and social science edition), 2018, 35(4): 6-13.)
[39] 和乐乐. 强国之道的反思：论秦代的法家思想及其走向[J]. 北京印刷学院学报, 2020, 28(6): 58-61. (HE L L. Reflection on the path to national strength: on legalism in the Qin dynasty and its development[J]. Journal of Beijing Institute of Graphic Communication, 2020, 28(6): 58-61.)

Options

Outlines

模态框（Modal）标题

Abstract

Cite this article

References