隨著科學論文發表數量的快速增長，引用來源的多樣性和格式差異增加了參考文獻剖析的難度。本研究旨在探討如何自動化擷取科學論文中的參考文獻，並利用人工智慧工具進行剖析，藉以簡化工作流程，降低人力和時間成本，並提升圖書館的知識傳播效能。本文提出了從中文期刊文章檔案中自動化擷取參考文獻的方法，並評估使用人工智慧工具剖析參考文獻的可行性。
本研究實驗分為三個部分，第一部分設計程式，擷取期刊文章中的參考文獻章節；第二部分評估不同人工智慧工具在參考文獻剖析任務中的效能；第三部分根據第二部分的實驗結果修正實驗方法，並評估和比較修正後的成果。實驗結果如下：
1. 在參考文獻擷取實驗中，基於規則方法的程式能夠自動擷取文章中的參考文獻內容，用於建立資料集作為後續研究基礎。
2. 在參考文獻剖析實驗中，本研究比較了spaCy和ChatGPT兩種基於Transformer架構的人工智慧工具的效能。實驗結果顯示，ChatGPT在各欄位的F1-score表現優於spaCy，具有較高的準確性和穩定性。
3. 在第三部分實驗中，選擇了第二部分中效能較佳的ChatGPT進行提示修正。實驗結果顯示，經過提示調整後，ChatGPT在各欄位的F1-score表現均有所提升。
本研究結果顯示了使用人工智慧工具自動化剖析參考文獻的可行性，並展現了大型語言模型在這一任務中的潛力和優勢。未來研究可以進一步嘗試結合多種人工智慧工具，探討利用不同模型優勢提升參考文獻剖析的準確性，同時探討減低剖析成本的可能性。

With the rapid growth in the number of scientific publications, the diversity of citation styles has increased the difficulty of reference parsing. This thesis aims to discuss how to automate the extraction and parsing of references from scientific papers using artificial intelligence tools, thereby simplifying workflows, reducing time costs, and enhancing the efficiency of knowledge dissemination in libraries. This paper proposes a method for extracting references from Chinese journal articles and evaluates the feasibility of parsing these references using AI tools.
The study is divided into three parts. The first part involves extracting reference sections from journal articles. The second part assesses the performance of different AI tools in the task of reference parsing. The third part modifies the experimental methods based on the results of the second part and evaluates and compares the outcomes after these adjustments. The experimental results are as follows:
1. In the first experiment, the rule-based program successfully extracted reference content from the articles in their entirety.
2. The second experiment compared the performance of two AI tools, spaCy and ChatGPT, both based on the Transformer architecture, in reference parsing. Results showed that ChatGPT outperformed spaCy in terms of F1-score, indicating higher accuracy and stability.
3. In the third experiment, ChatGPT, which demonstrated better performance in the second part, was selected for model adjustments. We optimized the prompt, and the results indicated that after adjustments, ChatGPT's F1-score performance improved across all fields.
In summary, the results of this study demonstrate the feasibility of parsing references using AI tools and reveal the potential of large language models in this task. Future research could explore further integration of various artificial intelligence tools to enhance the accuracy of this task, as well as possibilities for reducing the costs.

馬行遠、李韋杰 、劉昭麟（2022 年 11 月 21-22 日）。中文醫療文件的命名實體辨識報告。The 34th Conference on Computational Linguistics and Speech Processing。台北市，台灣。
陳光華 （2003） 。引文索引與臺灣學術期刊之經營。人文與社會科學簡訊，10：3卷，68-81。
曾淑賢、鄭秀梅、羅金梅（2013）。臺灣連結世界・世界認識臺灣―「臺灣人文及社會科學引文索引資料庫」建置經驗。國家圖書館館刊，102（2），139-171。
BibPro: A Citation Parser Based on Sequence Alignment Techniques | IEEE Conference Publication | IEEE Xplore. (n.d.). Retrieved 19 December 2023, from https://ieeexplore.ieee.org/document/4483078
Blair-Stanek, A., Holzenberger, N., & Van Durme, B. (2023). Can GPT-3 Perform Statutory Reasoning? Proceedings of the Nineteenth International Conference on Artificial Intelligence and Law, 22–31. https://doi.org/10.1145/3594536.3595163
Blecher, L., Cucurull, G., Scialom, T., & Stojnic, R. (2023). Nougat: Neural Optical Understanding for Academic Documents (arXiv:2308.13418). arXiv. https://doi.org/10.48550/arXiv.2308.13418
Brzustowicz, R. (2023). From ChatGPT to CatGPT: The Implications of Artificial Intelligence on Library Cataloging. Information Technology and Libraries, 42(3), Article 3. https://doi.org/10.5860/ital.v42i3.16295
C. -C. Chen, K. -H. Yang, H. -Y. Kao, & J. -M. Ho. (2008). BibPro: A Citation Parser Based on Sequence Alignment Techniques. 22nd International Conference on Advanced Information Networking and Applications - Workshops (Aina Workshops 2008), 1175–1180. https://doi.org/10.1109/WAINA.2008.125
Chen, Y., Lasko, T. A., Mei, Q., Denny, J. C., & Xu, H. (2015). A study of active learning methods for named entity recognition in clinical text. Journal of Biomedical Informatics, 58, 11–18. https://doi.org/10.1016/j.jbi.2015.09.010
Cho, S., Jeong, S., Seo, J. yeon, & Park, J. (2023). Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker. In A. Rogers, J. Boyd-Graber, & N. Okazaki (Eds.), Findings of the Association for Computational Linguistics: ACL 2023 (pp. 960–971). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.findings-acl.61
Choi, J. H., Hickman, K. E., Monahan, A., & Schwarcz, D. (2023). ChatGPT Goes to Law School (SSRN Scholarly Paper 4335905). https://doi.org/10.2139/ssrn.4335905
Cioffi, A., & Peroni, S. (2022). Structured references from PDF articles: Assessing the tools for bibliographic reference extraction and parsing (arXiv:2205.14677). arXiv. https://doi.org/10.48550/arXiv.2205.14677
Councill, I., Giles, C. L., & Kan, M.-Y. (2008). ParsCit: An Open-source CRF Reference String Parsing Package. In N. Calzolari, K. Choukri, B. Maegaard, J. Mariani, J. Odijk, S. Piperidis, & D. Tapias (Eds.), Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08). European Language Resources Association (ELRA). http://www.lrec-conf.org/proceedings/lrec2008/pdf/166_paper.pdf
Dai, S., Shao, N., Zhao, H., Yu, W., Si, Z., Xu, C., Sun, Z., Zhang, X., & Xu, J. (2023). Uncovering ChatGPT’s Capabilities in Recommender Systems. Proceedings of the 17th ACM Conference on Recommender Systems, 1126–1132. https://doi.org/10.1145/3604915.3610646
Fantechi, A., Gnesi, S., Livi, S., & Semini, L. (2021). A spaCy-based tool for extracting variability from NL requirements. 32–35. https://doi.org/10.1145/3461002.3473074
Gemini Team, R. Anil, S. Borgeaud, Y. Wu, J.-B. Alayrac, J. Yu, R. Soricut, J. Schalkwyk, A. M. Dai, A. Hauth, et al. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805, 2023.
Guangshang, G. a. O. (2022). Survey on Attention Mechanisms in Deep Learning Recommendation Models. Computer Engineering and Applications, 58(9), 9. https://doi.org/10.3778/j.issn.1002-8331.2112-0382
Hadi, M. U., Al-Tashi, Q., Qureshi, R., Shah, A., Muneer, A., Irfan, M., Zafar, A., Shaikh, M., Akhtar, N., Wu, J., & Mirjalili, S. (2023). Large Language Models: A Comprehensive Survey of its Applications, Challenges, Limitations, and Future Prospects. https://doi.org/10.36227/techrxiv.23589741.v3
Hu, C., Gong, H., & He, Y. (2022). Data driven identification of international cutting edge science and technologies using SpaCy. PLOS ONE, 17(10), e0275872. https://doi.org/10.1371/journal.pone.0275872
Islam, S., Elmekki, H., Elsebai, A., Bentahar, J., Drawel, N., Rjoub, G., & Pedrycz, W. (2023). A comprehensive survey on applications of transformers for deep learning tasks. Expert Systems with Applications, 241, 122666. https://doi.org/10.1016/j.eswa.2023.122666
Keretna, S., Lim, C. P., & Creighton, D. (2014). A hybrid model for named entity recognition using unstructured medical text. 2014 9th International Conference on System of Systems Engineering (SOSE), 85–90. https://doi.org/10.1109/SYSOSE.2014.6892468
Khabsa, M., & Giles, C. L. (2014). The number of scholarly documents on the public web. PloS One, 9(5), e93949. https://doi.org/10.1371/journal.pone.0093949
Lin, T., Wang, Y., Liu, X., & Qiu, X. (2022). A survey of transformers. AI Open, 3, 111–132. https://doi.org/10.1016/j.aiopen.2022.10.001
Liu, P., Guo, Y., Wang, F., & Li, G. (2022). Chinese named entity recognition: The state of the art. Neurocomputing, 473, 37–53. https://doi.org/10.1016/j.neucom.2021.10.101
Lund, B., & Ting, W. (2023). Chatting about ChatGPT: How May AI and GPT Impact Academia and Libraries? (SSRN Scholarly Paper 4333415). https://doi.org/10.2139/ssrn.4333415
Matelsky, J. K., Parodi, F., Liu, T., Lange, R. D., & Kording, K. P. (2023). A large language model-assisted education tool to provide feedback on open-ended responses (arXiv:2308.02439). arXiv. https://doi.org/10.48550/arXiv.2308.02439
Nguyen, M. V., Lai, V. D., Pouran Ben Veyseh, A., & Nguyen, T. H. (2021). Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing. In D. Gkatzia & D. Seddah (Eds.), Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations (pp. 80–90). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.eacl-demos.10
Nov, O., Singh, N., & Mann, D. (2023). Putting ChatGPT’s Medical Advice to the (Turing) Test: Survey Study. JMIR Medical Education, 9, e46939. https://doi.org/10.2196/46939
OpenAI. (2023). GPT-4 Technical Report (arXiv:2303.08774). arXiv. http://arxiv.org/abs/2303.08774
Panda, S., & Kaur, N. (2023). Exploring the viability of ChatGPT as an alternative to traditional chatbot systems in library and information centers. Library Hi Tech News, 40(3), 22–25. https://doi.org/10.1108/LHTN-02-2023-0032
Perera, N., Dehmer, M., & Emmert-Streib, F. (2020). Named Entity Recognition and Relation Detection for Biomedical Information Extraction. Frontiers in Cell and Developmental Biology, 8, 673. https://doi.org/10.3389/fcell.2020.00673
Prasad, A., Kaur, M., & Kan, M.-Y. (2018). Neural ParsCit: A deep learning-based reference string parser. International Journal on Digital Libraries, 19(4), 323–337. https://doi.org/10.1007/s00799-018-0242-1
Rodrigues Alves, D., Colavizza, G., & Kaplan, F. (2018). Deep Reference Mining From Scholarly Literature in the Arts and Humanities. Frontiers in Research Metrics and Analytics, 3, 21. https://doi.org/10.3389/frma.2018.00021
Saha, S., & Ekbal, A. (2013). Combining multiple classifiers using vote based classifier ensemble technique for named entity recognition. Data & Knowledge Engineering, 85, 15–39. https://doi.org/10.1016/j.datak.2012.06.003
Sasaki, Y., Tsuruoka, Y., McNaught, J., & Ananiadou, S. (2008). How to make the most of NE dictionaries in statistical NER. BMC Bioinformatics, 9 Suppl 11(Suppl 11), S5. https://doi.org/10.1186/1471-2105-9-S11-S5
Son, G., Jung, H., Hahm, M., Na, K., & Jin, S. (2023). Beyond Classification: Financial Reasoning in State-of-the-Art Language Models (arXiv:2305.01505). arXiv. https://doi.org/10.48550/arXiv.2305.01505
Song, M., Yu, H., & Han, W.-S. (2015). Developing a hybrid dictionary-based bio-entity recognition technique. BMC Medical Informatics and Decision Making, 15(1), S9. https://doi.org/10.1186/1472-6947-15-S1-S9
Tang, R., Han, X., Jiang, X., & Hu, X. (2023). Does Synthetic Data Generation of LLMs Help Clinical Text Mining? (arXiv:2303.04360). arXiv. https://doi.org/10.48550/arXiv.2303.04360
Tkaczyk, D., Collins, A., Sheridan, P., & Beel, J. (2018). Machine Learning vs. Rules and Out-of-the-Box vs. Retrained: An Evaluation of Open-Source Bibliographic Reference and Citation Parsers (arXiv:1802.01168). arXiv. https://doi.org/10.48550/arXiv.1802.01168
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., Rodriguez, A., Joulin, A., Grave, E., & Lample, G. (2023). LLaMA: Open and Efficient Foundation Language Models (arXiv:2302.13971). arXiv. https://doi.org/10.48550/arXiv.2302.13971
Trautmann, D., Petrova, A., & Schilder, F. (2022). Legal Prompt Engineering for Multilingual Legal Judgement Prediction (arXiv:2212.02199). arXiv. https://doi.org/10.48550/arXiv.2212.02199
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is All you Need. Advances in Neural Information Processing Systems, 30. https://papers.nips.cc/paper_files/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html
Yang, K., Ji, S., Zhang, T., Xie, Q., & Ananiadou, S. (2023). On the Evaluations of ChatGPT and Emotion-enhanced Prompting for Mental Health Analysis.
Zhang, B., Yang, H., & Liu, X.-Y. (2023). Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models (SSRN Scholarly Paper 4489831). https://doi.org/10.2139/ssrn.4489831
Zhang, X., Zou, J., Le, D. X., & Thoma, G. R. (2011). A structural SVM approach for reference parsing. BMC Bioinformatics, 12(3), S7. https://doi.org/10.1186/1471-2105-12-S3-S7
Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., Du, Y., Yang, C., Chen, Y., Chen, Z., Jiang, J., Ren, R., Li, Y., Tang, X., Liu, Z., … Wen, J.-R. (2023, March 31). A Survey of Large Language Models. https://arxiv.org/abs/2303.18223v13
Zhao, J., Huang, F., Lv, J., Duan, Y., Qin, Z., Li, G. & Tian, G.. (2020). Do RNN and LSTM have Long Memory?. Proceedings of the 37th International Conference on Machine Learning, 119(113), 65-11375.