近年來因科技進步，生成式人工智慧工具的出現，大幅改變了原先的工作模式。隨著技術的成熟，GAI已逐漸轉變為可輔助內容產製與知識組織的重要工具，並廣泛應用於教育、設計、媒體與文化內容生產等領域。在文化與策展實務中，展覽內容的規劃與敘事高度仰賴策展者對資訊的整合能力與詮釋判斷，而GAI的導入，可能改變傳統需耗費大量人力的策展流程，使內容生成、資料整理與展覽敘事方式產生新的可能性。
然而，生成式AI在策展情境中的實際表現仍存在需經過檢驗之處，包括其生成內容在專業正確性、敘事一致性、觀眾可理解性，以及價值傳達效果等方面，是否能滿足展覽實務需求。因此，本研究聚焦於生成式人工智慧應用於數位策展與檔案展覽之內容生成表現，透過不同工具之比較與評估，探討其在策展流程中的角色定位、應用潛力以及優勢與劣勢。
因此，本研究首先由專家針對ChatGPT、Claude與Gemini三種生成式AI工具，以檔案修復為主題所生成之展覽內容進行評估，並依據評估結果選取表現最佳之生成版本，進一步轉化為實際之數位展覽內容。其後，再由觀展者進行實際瀏覽與體驗評估，以比較不同使用者角色對於展覽內容品質與觀展體驗之感受差異。
研究結果顯示，專家對於三種GAI工具整體皆展現中高程度之正向表現，具備支援策展內容生成與輔助策展規劃之潛力。其中，ChatGPT在內容結構穩定性與敘事一致性方面表現較為均衡；Claude在專業性與內容深度上相對突出；Gemini則在知識密度與學術取向上較為明顯，但在部分構面之評價分布較為分散。
將專家與觀展者評估結果進行進一步比對發現，專家與觀展者之評價整體趨勢一致，皆肯定GAI生成內容於展覽設計中的應用價值，且觀展者之正向評價普遍略高於專家，顯示使用者在實際觀看體驗上對GAI生成內容之接受度較高。然而，專家評價相對較為保守，反映其在專業判準上更重視內容精確性與策展邏輯一致性。GAI已可作為數位策展流程中之輔助工具，特別適用於前期發想與內容架構建構階段，但仍需仰賴策展專業進行內容篩選、修正與整合，以確保展覽品質與知識傳達之正確性與深度。

In recent years, driven by technological advancements, the emergence of generative artificial intelligence tools has significantly transformed traditional workflows. As technology has matured, GAI has gradually evolved into an important tool that supports content production and knowledge organization, and has been widely applied in fields such as education, design, media, and cultural content production. In the context of culture and curatorial practice, the planning and narration of exhibition content heavily rely on curators’ ability to integrate information and make interpretive judgments. The introduction of GAI may transform traditional curatorial processes that require substantial human labor, creating new possibilities for content generation, data organization, and the construction of exhibitions.
However, the actual performance of generative AI in curatorial contexts still requires further examination, particularly in terms of accuracy, narrative consistency, audience comprehensibility, and the effectiveness of value communication, to determine whether it can meet practical exhibition needs. Therefore, this study focuses on the performance of generative artificial intelligence in content generation for digital curation and archival exhibitions, and explores its role, application potential, advantages, and limitations in the curatorial process through a comparative evaluation of different tools.
Accordingly, this study first invited experts to evaluate exhibition content generated by three generative AI tools, ChatGPT, Claude, and Gemini, based on the theme of archival preservation. Based on the evaluation results, the best-performing generated version was selected and further developed into a digital exhibition. Subsequently, visitors were invited to browse and evaluate the exhibition to compare differences in perceptions of content quality and user experience across different groups.
The results show that experts generally rated the three GAI tools as demonstrating moderately high positive overall performance, indicating their potential to support exhibition content generation and assist in curatorial planning. Among them, ChatGPT performed relatively balanced in terms of structural stability and narrative consistency; Claude demonstrated strengths in professional depth and content richness; and Gemini exhibited higher knowledge density and a more academic orientation, though its evaluation distribution was relatively more dispersed across dimensions.
A further comparison between expert and visitor evaluations revealed a consistent overall trend. Both groups affirmed the value of GAI-generated content in exhibition design, with visitors generally providing slightly higher ratings than experts, suggesting a relatively higher level of acceptance among users in actual viewing experiences. However, expert evaluations were comparatively more conservative, reflecting a stronger emphasis on content accuracy and curatorial logical consistency. Overall, GAI can serve as a supportive tool in digital curatorial workflows, particularly in the early ideation and structural development stages. Nevertheless, it still relies on curatorial expertise for content selection, refinement, and integration to ensure the accuracy and depth of knowledge communication and exhibition quality.

American Alliance of Museums (2012). Standards for Museum Exhibitions and Indicators of Excellence.
artsteps (2025). Homepages. https://www.artsteps.com/
ARTTOGO (2025).Homepages.https://artogo.co/zh-TW
Bandi, A., Adapa, P. V. S. R., & Kuchi, Y. E. V. P. K. (2023). The power of generative ai: A review of requirements, models, input–output formats, evaluation metrics, and challenges. Future Internet, 15(8), 260.
Benzon, W. L. (2025). From LLM mechanisms to ring-composition: A conversation with Claude 3.5 Working Paper. Available at SSRN.
Boss, G. J. (2020). Teaching global citizen-leadership by design: expanding learning opportunities through web-based digital curation tools. Handbook of Teaching with Technology in Management, Leadership, and Business , 337-346. https://doi.org/10.4337/9781789901658.00042
Chen, S., & Li, M. (2024). AI for Cataloging and Metadata Creation: Perspectives and Future Opportunities from Cataloging and Metadata Professionals. Technical Services Quarterly, 41(4), 317-332.
Corchado, J. M., López, S., Garcia, R., & Chamoso, P. (2023). Generative artificial intelligence: fundamentals. ADCAIJ: advances in distributed computing and artificial intelligence journal, 12(1), e31704-e31704.
Damala, A., Ruthven, I., & Hornecker, E. (2019). The MUSETECH Companion: Navigating the Matrix.
De Silva, D., Jayatilleke, S., El-Ayoubi, M., Issadeen, Z., Moraliyage, H., & Mills, N. (2024). The Human-Centred Design of a Universal Module for Artificial Intelligence Literacy in Tertiary Education Institutions. Machine Learning and Knowledge Extraction, 6(2), 1114-1125.
Derda, I., & Predescu, D. (2025). Towards human-centric AI in museums: practitioners’ perspectives and technology acceptance of visitor-centered AI for value (co-)creation [Article]. Museum Management and Curatorship, 40(4), 532-554. https://doi.org/10.1080/09647775.2025.2467703
Dickey, E. ( 2024). Act As If You Are a Curator: An AI-Generated Exhibition. Panorama: Journal of the Association of Historians of American Art 10 https://doi.org/ https://doi.org/10.24926/24716839.18990.
Dror, R., Hutchinson, D., Jones, M., Van Hyning, V., & Kuflik, T. (2024, June). The Curator's Helper. In Adjunct Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization, 496-504.
Elmourabit, Z., Retbi, A., & El Faddouli, N. E. (2024). The Impact of Generative Artificial Intelligence on Education: A Comparative Study. In European Conference on e-Learning (Vol. 23, No. 1, pp. 470-476). Academic Conferences International Limited.
europeana (2025).Homepages.https://www.europeana.eu/en
Exhibit (2025).Homepages.https://www.exhibit.so/
Fidel, R. (1984). The case study method: A case study. Library and Information Science Research, 6(3), 273-288.
Gao, Z., Guo, M., Chen, Y., Xu, D., & Wang, Z. (2024, June). The Digital Blossoming: Generative Flowers of Ethnic Wisdom. In Proceedings of the 16th Conference on Creativity & Cognition (pp. 532-536).
Google Arts& Culture (2025).Homepages.https://artsandculture.google.com/
Graham, B., & Cook, S. (2010). Rethinking Curating: Art after New Media-Leonardo Books. The MIT Press.
Higgins, S. (2011). Digital curation: the emergence of a new discipline. International Journal of Digital Curation, 6(2), 78-88.
Huang, P. C., Li, I. C., Wang, C. Y., Shih, C. H., Srinivaas, M., Yang, W. T., Kao, C. F., & Su, T. J. (2025). Integration of Artificial Intelligence in Art Preservation and Exhibition Spaces [Article]. Applied Sciences (Switzerland), 15(2), Article 562. https://doi.org/10.3390/app15020562
Islam, R., & Ahmed, I. (2024). Gemini-the most powerful LLM: Myth or Truth. 2024 5th Information Communication Technologies Conference (ICTC),
Jiang, N., Liu, X., Liu, H., Lim, E. T. K., Tan, C.-W., & Gu, J. (2023). Beyond AI-powered context-aware services: the role of human–AI collaboration. Industrial management + data systems, 123(11), 2771-2802. https://doi.org/10.1108/IMDS-03-2022-0152
Jiang, R., He, X., Zhang, S., Zhou, Y., & Han, Y. (2025). Generative Artificial Intelligence Enables Multiple Learning Environments and Implementation Paths. Proceedings of the 2024 7th International Conference on Educational Technology Management, 1-193. https://doi.org/10.1145/3711403.3711436 (ICETM 2024: 2024 the 7th International Conference on Educational Technology Management)
Khan, S., & Bhatt, I. (2019). Curation. The international encyclopedia of media literacy, 1-9.
Kshetri, N., Sharma, R., & Shaikh, A. A. (2025). Economic and Social Impacts of Generative Artificial Intelligence [Review]. IT Professional, 27(2), 17-20. https://doi.org/10.1109/MITP.2025.3552884
Kun, P., Freiberger, M. A., Løvlie, A. S., & Risi, S. (2024, July). GenFrame–Embedding Generative AI Into Interactive Artifacts. In Proceedings of the 2024 ACM Designing Interactive Systems Conference, 714-727.
Lo, L. S. (2023). The art and science of prompt engineering: a new literacy in the information age. Internet Reference Services Quarterly, 27(4), 203-210.
Mallikarjuna, B., Chittemsetty, P. (2024). Generative Artificial Intelligence: Fundamentals and Evolution. In: Raza, K., Ahmad, N., Singh, D. (eds) Generative AI: Current Trends and Applications. Studies in Computational Intelligence, vol 1177. Springer, Singapore. https://doi.org/10.1007/978-981-97-8460-8_1
Mao, R., Chen, G., Zhang, X., Guerin, F., & Cambria, E. (2023). GPTEval: A survey on assessments of ChatGPT and GPT-4. arXiv preprint arXiv:2308.12488.
McGinley, M. (2007). The legal environment of digital curation–a question of balance for the digital librarian. In Research and Advanced Technology for Digital Libraries: 11th European Conference, ECDL 2007, Budapest, Hungary, September 16-21, 2007. Proceedings 11 (pp. 534-538). Springer Berlin Heidelberg.
Mensa, E., & Damiano, R. (2024). From plot to prompts: a case study on interactive narratives in museums. CEUR WORKSHOP PROCEEDINGS,
Meskó, B. (2023). Prompt Engineering as an Important Emerging Skill for Medical Professionals: Tutorial [Article]. Journal of Medical Internet Research, 25(1), Article e50638. https://doi.org/10.2196/50638
Moulaison-Sandy, H., & Coble, Z. (2024). Leveraging AI in cataloging: What works, and why?. Technical Services Quarterly, 41(4), 375-383.
Murphy, C., Carew, P. J., & Stapleton, L. (2023). A human-centred systems manifesto for smart digital immersion in Industry 5.0: a case study of cultural heritage. AI & Society, 1-16.
Oyelude, A. A. (2019). Emerging technologies for libraries archives and museums: trends and projections. Library Hi Tech News, 36(1), 13-14.
Ribeiro, M., Santos, J., Lobo, J., Araújo, S., Magalhães, L., & Adão, T. (2024). VR, AR, gamification and AI towards the next generation of systems supporting cultural heritage: addressing challenges of a museum context. In Proceedings of the 29th International ACM Conference on 3D Web Technology (pp. 1-10). Guimarães Portugal: ACM. doi:10.1145/3665318.3677172
Roopa, S., & Rani, M. S. (2012). Questionnaire designing for a survey. Journal of Indian Orthodontic Society, 46(4_suppl1), 273-277.
Ruijuan, L. V., Jingbei, Z. H. A. N. G., Dan, Y. A. N., & Yingchun, C. A. I. (2023). Innovative Development of AIGC and GLAM: Review of" Shaping the Future: AIGC and GLAM Innovative Development" Cutting-Edge Academic Forum. Journal of Library and Information Sciences in Agriculture, 35(5), 27-36. https://doi.org/10.13998/j.cnki.issn1002-1248.23-0424
Sai, N. (2025). Research on the Status Quo of Rural Teaching Based on Generative Artificial Intelligence. ICETM 2024 - Proceedings of the 2024 7th International Conference on Educational Technology Management,
Sasson Lazovsky, G., Raz, T., & Kenett, Y. N. (2025). The art of creative inquiry—from question asking to prompt engineering. The Journal of Creative Behavior, 59(1), e671.
Serrell, B. (2017). Judging exhibitions: A framework for assessing excellence. Routledge.
Short, C. E., & Short, J. C. (2023). The artificially intelligent entrepreneur: ChatGPT, prompt engineering, and entrepreneurial rhetoric creation. Journal of Business Venturing Insights, 19, e00388. https://doi.org/https://doi.org/10.1016/j.jbvi.2023.e00388
Sobo, A., Mubarak, A., Baimagambetov, A., & Polatidis, N. (2025). Evaluating LLMs for code generation in HRI: A comparative study of ChatGPT, gemini, and claude. Applied Artificial Intelligence, 39(1), 2439610.
Spennemann, D. H. R. (2023). Exhibiting the heritage of COVID-19—A conversation with ChatGPT. Heritage, 6（8）, 5732-5749. https://doi.org/10.3390/heritage6080302
Svendsen, A., & Garvey, B. (2023). An Outline for an Interrogative/Prompt Library to help improve output quality from Generative-AI Datasets. Prompt Library to help improve output quality from Generative-AI Datasets (May 2023).
Taherdoost, H. (2016). Validity and reliability of the research instrument; how to test the validation of a questionnaire/survey in a research. International Journal of Academic Research in Management (IJARM), 5. (pp. 28-36).
van Strien, D., Bell, M., McGregor, N. R., & Trizna, M. (2022, March). An Introduction to AI for GLAM. In Proceedings of the second teaching machine learning and artificial intelligence workshop (pp. 20-24). PMLR.
Vasic, I., Fill, H. G., Quattrini, R., & Pierdicca, R. (2024). LLM-aided museum guide: Personalized tours based on user preferences. In International Conference on Extended Reality (pp. 249-262). Cham: Springer Nature Switzerland.
Virsody (2025).Homepages.https://virsody.io/
Wolff, A., & Mulholland, P. (2013, May). Curation, curation, curation. In Proceedings of the 3rd Narrative and Hypertext Workshop (pp. 1-5).
Xu, J., & Pan, Y. (2024). The future museum: Integrating augmented reality (AR) and virtual-text with AI-enhanced information systems. Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications(JoWUA), 15(3), 373-394.
Yeğinsü, İ. (2025). The impact of Artificial Intelligence on the “curator-as-artist”: revisiting Ventzislavov’s concept in two cases of AI-based curating [Article]. AI and Society. https://doi.org/10.1007/s00146-025-02462-z
Zhang, Z., Zhang, J., Zhang, X., & Mai, W. (2025). A comprehensive overview of Generative AI (GAI): Technologies, applications, and challenges [Short survey]. Neurocomputing, 632, Article 129645.https://doi.org/10.1016/j.neucom.2025.129645
丁振卿、黃紫娟、林昱辰（2024）。生成式AI輔助寫作研究。冷凍空調&能源科技（146），24-37。 https://doi.org/10.29911/jehvace_new.202407_(146).0001
王麗蕉、何祖鳳、林人立、林巧敏、林俊銘、邱玉鳳、邱菊梅、孫筱娟、許尹馨、許芳銘、張玉華、張聰明、連秀芬、陳淑美、陳穆怡、陸雯玉、莊道明、楊曉雯、蔡斐文、蕭智仁、薛理桂、魏雅惠（2021）。檔案管理總論。新北市：國家發展委員會檔案管理局。
石侃、蘇超、盧昱波（2019）。人工智慧（AI）：博物館未來發展的必要工具。科技博物，23（1），29-41。
吳奕祥。（2023）。圖書館數位策展實務初探－以國立臺灣圖書館電子資源線上展覽為例。臺北市立圖書館館訊，37（1），29-45。
吳紹群。（2022）。博物館5G技術應用於文物導覽之個案研究－以AI及AR智慧眼鏡實驗服務為例。博物館學季刊，36（4），111–127。doi： 10.6686/MuseQ.202210_36(4).0006
李亞祝。（2023）。國家檔案融於展覽暨教學之研究－以美國國家檔案為例。檔案半年刊，22（2），126–135。
周雅容（1997）。焦點團體法在調查研究上的應用。調查研究,(3), 52-73.
林巧敏（2012）。檔案應用服務。臺北市：文華。
林巧敏（2014）。檔案展覽：文集與圖錄（初版）。臺北市：國立政治大學人文中心。
林平（2005）。藝術展覽的價值和空間的關係。博物館學季刊，19 1），29– 37。doi：10.6686/MuseQ.200501_19(1).0003
林明誼、林新發（2024）。 AI時代跨領域人機協作之運用策略及有關倫理議題. 臺灣教育評論月刊，13(10)，19-26。
林芯瑜。（2023）。混合實境於虛實整合數位策展應用與成效評估。[博碩士論文，國立政治大學]。臺灣碩博士論文知識加值系統。
林金定、嚴嘉楓、陳美花（2005）。質性研究方法：訪談模式與實施步驟分析。身心障礙研究季刊, 3(2), 122-136. https://doi.org/10.30072/jdr.200506.0005
施登騰（2021）。從缺陷到對話到創作－論博物館科技的「共享權威」與「數位策展」實踐。清華藝術學報，(3)，129-154。https://doi.org/10.6922/THJAR.202112_(3).0007
柯皓仁、楊美華、林素甘（2008）。數位化發展對檔案應用服務之影響。檔案季刊，7（1），4–21。
范麗娟。（1994）。深度訪談簡介。戶外遊憩研究，7（2），25-35。
時空旅行社 國家文化記憶庫2.0 線上策展平臺（2025）。首頁。 https://curation.culture.tw/Curation/Articles?a=69
區琬琳（2017）。檔案展覽永續經營。檔案半年刊，16（1），134–141。
張淑惠。（2003）。檔案展覽之規劃與實務運作。檔案季刊，2（2），89-98。
張鈞傑、黃茂榮、黃瀞慧。（2024）。 AI影像辨識技術輔助博物館藏品盤點之初探－以國立臺灣歷史博物館為例。科技博物, 28(2), 31-49.
章美英、許麗齡（2006）。質性研究－焦點團體訪談法之簡介與應用。護理雜誌, 53(2), 67-72. https://doi.org/10.6224/jn.53.2.67
陳奕廷, & 陳品妤。（2024）。生成式AI在博物館數據分析之應用與效益－以國立自然科學博物館為例。科技博物, 28(4), 5-28.
陳憶華。（2007）。檔案展覽探析－兼論國史館歷年舉辦之展覽。檔案季刊，6（3），55-71。
開放博物館（2025）。首頁。https://openmuseum.tw/
黃光男（2006）。博物館展覽理念與規劃。書畫藝術學刊，1–14。doi： 10.29831/TDPC.200612.0001
黃宇暘、郭鎮武、周維強、林國平、蔡瑞煌。（2021）。人工智慧在中文歷史文獻判讀領域應用初探：以國立故宮博物院典藏為例。科技博物, 25(3), 5-23.
黃靖斐、陳志銘（2018）。數位內容策展在大學校史館的協作與應用。圖資與檔案學刊（93），75-106。https://doi.org/10.6575/jila.201812_(93).0004
葉乃嘉（2013）。研究方法的第一本書：教育、人文與社會科學研究的入門書。五南圖書。
解昆樺（2023）。數位典藏到策展的公共加值：中研院「開放博物館」之圖書館數位策展設計與議題觸發。臺北市立圖書館館訊，37（1），46-59。
趙銀玲（2010）。民國檔案修復的實踐與認識。檔案管理, 6 , 90-90.
潘淑滿（2003）。質性研究：理論與應用。臺北市：心理。
蔡柏瑄（2016）。遊戲化概念導入數位策展於歷史文物推廣之研究: 以某國書個案為例。[博碩士論文，臺灣師範大學]。臺灣碩博士論文知識加值系統。
鄭緯筌（2024）。從文字到智慧：生成式人工智慧在出版產業的創新應用與挑戰探析。通識教育學報(12), 57-79. https://doi.org/10.6517/mcut.202412_(12).0003
檔案法（2008年7月2日）。https://law.moj.gov.tw/LawClass/LawAll.aspx?pcode=A0030134
薛理桂（1998）。檔案學導論（初版）。臺北市：漢美圖書。