[1] 中国图书馆学会. 中国图书馆学会关于印发《中国图书馆学会“十四五” 发展规划纲要（2021-2025年）》的通知[EB/OL]. [2025-09-24]. https://www.lsc.org.cn/cns/html_pass/contents/1299/15358.html. (Chinese Library Association. Notice of the Chinese Library Association on issuing the “14th Five-Year” Development Plan Outline of the Chinese Library Association (2021-2025)[EB/OL]. [2025-09-24]. https://www.lsc.org.cn/cns/html_pass/contents/1299/15358.html.)
[2] 中共中央办公厅、国务院办公厅. 关于推进实施国家文化数字化战略的意见[EB/OL]. [2025-09-24]. https://www.gov.cn/zhengce/2022-05/22/content_5691759.htm. (General Office of the Communist Party of China Central Committee, General Office of the State Council. Opinions on promoting the implementation of the National Cultural Digitalization Strategy[EB/OL]. [2025-09-24]. https://www.gov.cn/zhengce/2022-05/22/content_5691759.htm.)
[3] 国家图书馆. 国家图书馆“十四五” 发展规划[EB/OL]. [2025-09-24]. https://www.nlc.cn/upload/attachments/2023-04-14/4dd2526a.pdf. (National Library of China. 14th Five-Year Development Plan of the National Library of China[EB/OL]. [2025-09-24]. https://www.nlc.cn/upload/attachments/2023-04-14/4dd2526a.pdf.)
[4] 秦小林, 古徐, 李弟诚, 等. 大语言模型综述与展望[J]. 计算机应用, 2025, 45(3): 685-696. (QIN X L, GU X, LI D C, et al. Survey and prospect of large language models[J]. Journal of computer applications, 2025, 45(3): 685-696.)
[5] SHAO M H, ABDUL B, KARRI R, et al. Survey of different large language model architectures: trends, benchmarks, and challenges [J]. IEEE transactions on access, 2024, 12: 188664-188706.
[6] 李强, 林淑凤, 于媛. 生成式人工智能赋能科技查新的实践探索与模式构建[J]. 图书馆论坛, 2025, 45(8): 107-116. (LI Q, LIN S, YU Y. Generative ai-enhanced scientific novelty search: practical exploration and framework development[J]. Library tribune, 2025, 45(8): 107-116.)
[7] 张君冬, 杨松桦, 刘江峰, 等. AIGC赋能中医古籍活化:Huang-Di大模型的构建[J]. 图书馆论坛, 2024, 44(10): 103-112. (ZHANG J, YANG S, LIU J, et al. Aaigc empowering the revitalization of ancient books on traditional Chinese medicine：building the Huang-Di large language model[J]. Library tribune, 2024, 44(10): 103-112.)
[8] 徐鸿, 宋涵, 蒋莲.基于通义千问大模型的智慧馆员问答服务系统研究[J]. 高校图书馆工作, 2024, 44(6): 58-64. (XU H, SONG H, JIANG L. Research on the intelligent librarian Q&A service system based on Tongyi Qianwen large language model[J]. Library work in colleges and universities, 2024, 44(6): 58-64.)
[9] 李丽. 大语言模型视角下DeepSeek赋能高校图书馆学科服务研究[J]. 图书馆建设, 2025(3): 2782. (LI l. DeepSeek enabling university library subject services from the perspective of large language model[J]. Library development, 2025(3): 2782.)
[10] 郭亚军, 徐苑茜, 梁艳丽, 等. 从ChatGPT到DeepSeek：生成式人工智能迭代对图书馆的影响[J]. 图书馆论坛, 2025, 45(7): 140-149. (GUO Y, XU Y, LIANG Y, et al. From ChatGPT to DeepSeek: the impact of generative artificial intelligence iterations on libraries[J]. Library tribune, 2025, 45(7): 140-149.)
[11] 罗坤明, 李子晟, 张磊, 等. 国产开源大模型赋能图书馆智慧化服务功能——以DeepSeek为例[J]. 图书馆理论与实践, 2025(5): 86-96. (LUO K M, LI Z S, ZHANG L, et al. Empowering intelligent library services with domestic open-source large models: a case study of DeepSeek [J]. Library theory and practice, 2025(5): 86-96.
[12] 杨新涯, 戴立伟, 钱国富. DeepSeek在图书馆的应用场景构架研究[J]. 图书馆论坛, 2025, 45(10): 90-97. (YANG X Y, DAI L W, QIAN G F. Research on the application scenario architecture of DeepSeek in libraries[J]. Library tribune, 2025, 45(10): 90-97)
[13] 张强, 高颖, 任豆豆, 等. 融合DeepSeek-R1和RAG技术的先秦文化元典智能问答研究[J]. 现代情报, 2026, 46(1): 173-186. (ZHANG Q, GAO Y, REN D D, et al. Research on intelligent question answering for Pre-Qin cultural classics by integrating DeepSeek-R1 and RAG technologies[J]. Journal of modern information, 2026, 46(1): 173-186.)
[14] 张强, 高颖, 辛竹琳, 等. 多模型多视角下AI生成与学者撰写文献内容的比较研究[J]. 图书馆杂志, 2026, 45(5): 37-47. (ZHANG Q, GAO Y, XIN Z, et al. Comparative study of ai-generated and scholar-written literature content under multiple models and perspectives[J]. Library journal, 2026, 45(5): 37-47.)
[15] MA H, LU Y, XIAO Z, et al. SDD-Law LLM: advancing intelligent legal systems through synthetic data-driven fine-tuning of large language models [J]. Electronics (Switzerland), 2025, 14(4): 742.
[16] TORDJMAN M, LIU Z, YUCE M, et al. Comparative benchmarking of the DeepSeek large language model on medical tasks and clinical reasoning[J]. Nature medicine, 2025, 31: 2550–2555.
[17] JI T, GRAHAM Y, JONES G J F. Contrasting human opinion of non-factoid question answering with automatic evaluation [C]//2020 Conference on Human Information Interaction and Retrieval. New York: ACM, 2020: 348-352.
[18] HIJAZI H, MOLLá D, NGUYEN V, et al. Using large language models to evaluate biomedical query-focused summarization [C]//Proceedings of the 23rd Workshop on Biomedical Language Processing, Bangkok, Thailand: Association for Computational Linguistics, 2024: 236-242.
[19] BAKIR D, AKTA? M S, YILDIZ B. A model-based evaluation metric for question answering systems [J]. International journal of software engineering and knowledge engineering, 2025, 35(2): 243-262.
[20] ZHAO W, PEYRARD M, LIU F, et al. MoverScore: text generation evaluating with contextualized embeddings and earth mover distance[C]. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Hong Kong: Association for Computational Linguistics, 2019, 563-578.
[21] DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). Minneapolis: Association for Computational Linguistics, 2019: 4171-4186.
[22] ZHANG T, KISHORE V, WU F, et al. BERTSCORE: evaluating text generation with BERT [C]//Proceedings of the International Conference on Learning Representations. Addis Ababa: DBLP, 2020.
[23] PEINELT N, NGUYEN D, LIAKATA M. tBERT: topic models and BERT joining forces for semantic similarity detection [C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Online: Association for Computational Linguistics, 2020: 7047-7055.
[24] CHEN A, STANOVSKY G, SINGH S, et al. Evaluating question answering evaluation [C]//Proceedings of the 2nd Workshop on Machine Reading for Question Answering. Hong Kong: Association for Computational Linguistics, 2019: 119-124.
[25] 百度公司.文心ERNIE开发套件[EB/OL]. [2025-09-24]. https://ai.baidu.com/ai-doc/ERNIE-Ultimate/7l6367w4m.(Baidu Inc. ERNIE development kit[EB/OL]. [2025-09-24]. https://ai.baidu.com/ai-doc/ERNIE-Ultimate/7l6367w4m.)
[26] 火山引擎. Doubao-embedding-large— 火山方舟大模型服务平台[EB/OL]. [2025-09-24]. https://www.volcengine.com/docs/82379/1554711. (Volcengine. Doubao-embedding-large—Volcano Ark large model service platform[EB/OL]. [2025-09-24]. https://www.volcengine.com/docs/82379/1554711.)
[27] 路人与大师. BGE-M3：一个多功能、多语言、多粒度的语言向量模型[EB/OL]. [2025-09-24]. https://blog.csdn.net/weixin_41046245/article/details/142215886. (Luren Yudashi. BGE-M3: a multifunctional, multilingual, and multigranular language vector model[EB/OL]. [2025-09-24]. https://blog.csdn.net/weixin_41046245/article/details/142215886.)
[28] 北京人工智能研究院（BAAI）. BGE-M3模型官方文档[EB/OL]. [2025-09-24]. https://bge-model.com/bge/bge_m3.html. (Beijing Academy of Artificial Intelligence (BAAI). Official documentation of BGE-M3 model[EB/OL]. [2025-09-24]. https://bge-model.com/bge/bge_m3.html.)
[29] 智源社区（智能研究院）. 新一代通用向量模型BGE-M3：一站式支持多语言、长文本和多种检索方式[EB/OL]. [2025-09-24]. https://hub.baai.ac.cn/view/34816. (Baidu Institute of Artificial Intelligence (BAAI) Community. New-Generation general vector model BGE-M3: one-stop support for multilingual, long text and multiple retrieval methods[EB/OL]. [2025-09-24]. https://hub.baai.ac.cn/view/34816.)
[30] SATHEESH S, BECKH K, KLUG K, et al. Robustness evaluation of the German extractive question answering task[C]//Proceedings of the 31st International Conference on Computational Linguistics, COLING. Germany: Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS, 2025: 1785-1801.
[31] PENG C, GONG Z, SHEN G. Measurement and modeling of a web-based question answering system [J]. IEEE transactions on knowledge and data engineering, 2006, 18(7): 924-937.
[32] ASHRAFI T, INEZA Y, AREFIN S E, et al. Stable or shaky? The semantics of ChatGPT’s behavior under repeated queries [C]//2024 IEEE 18th International Conference on Semantic Computing (ICSC). Laguna Hills: IEEE, 2024: 110-116.
[33] 王芳, 魏中瀚, 连芷萱. 政务智能问答系统评价指标体系构建与测评问题编制[J]. 图书情报知识，2023, 40(6): 98-111. (WANG F, WEI Z H, LIAN Z X. Developing an evaluation index system and its testing questions for government intelligent Q&A systems[J]. Documentation, information & knowledge, 2023, 40(6): 98-111.)
[34] RAWAT P, MEHTA S, BAJAJ M, et al. A multi-source information retrieval system for question answering with sentiment analysis and LLM interpretation [C]//2024 International Conference on Automation and Computation (AUTOCOM). Dehradun: IEEE, 2024: 1-6.
[35] PALNISAMY A M, SANGEETHA S, NATARAJ R V. Effects of SQL query inclusive computation in application response time [J]. Journal of computational and theoretical nanoscience, 2018, 15(5): 1625-1628.
[36] HADDAD S, MOKDAD L, YOUCEF S. Response time of BPEL4WS constructors [C]//The IEEE symposium on Computers and Communications. Riccione: IEEE, 2010: 695-700.
[37] GAO M, LI M, JI T, et al. Key technologies of intelligent question-answering system for power system rules and regulations based on improved BERTserini algorithm [J]. Processes, 2024, 12(1): 58.
[38] DERIU J, RODRIGO A, OTEGI A, et al. Survey on evaluation methods for dialogue systems. Artificial intelligence review. 2021, 54(1): 755-810.
[39] SUN M T, LIU L, CHEN H. An answer quality evaluation algorithm based on semantic in community-based question answering [C]//201814th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD). Beijing: IEEE, 2018: 971-978.
[40] XIONG M X, LI A P, XIE Z S, et al. A practical approach to answer extraction for constructing QA solution [C]//2018 IEEE Third International Conference on Data Science in Cyberspace. Changsha: IEEE, 2018: 398-404.
[41] 同济大学信息办.同济大学AI应用创新平台正式上线[EB/OL]. [2025-09-24]. https://mp.weixin.qq.com/s/VkJ10cZS-j3-fVBvvoWkoQ.(Information Office of Tongji University. Tongji University AI application innovation platform officially launched[EB/OL]. [2025-09-24]. https://mp.weixin.qq.com/s/VkJ10cZS-j3-fVBvvoWkoQ.)
[42] YU M, ZHOU R, CAI Z, et al. Unravelling the relationship between response time and user experience in mobile applications[J]. Internet research, 2020, 30(5): 1353-1382.
