Reliability and Domain Limitations of Intelligent Virtual Assistants in Digital Heritage Systems
DOI:
https://doi.org/10.55630/dipp.2026.16.18Keywords:
AI Assistant, Cultural Heritage Assistants, RAG, PEFT, LLM ReliabilityAbstract
After years of work on cultural heritage and scientific digitization, the world accumulated a vast amount of data and information. Although digital data is far more accessible than the physical one, even in an unstructured way, better interaction is needed by the non-professional users. At the same time AI-related systems gain widespread popularity in all kinds of platforms, easing accessibility. Digital assistants and chatbots are implemented in existing applications and databases. Cultural heritage areas are not falling behind. Plenty of examples of using such systems in the field are already available. Implementation of AI in cultural heritage brings unique challenges along with benefits. The accuracy of the models is highly uncertain, caused by the specifics of the cultural heritage data. Several approaches to overcome the challenges such as parameter-efficient fine-tuning and Retrieval-Augmented Generation are examined.References
Agbesi, V., Chen, W., Yussif, S., Hossin, M., Chiagoziem, U., Kuadey, N., Agbesi, C., Samee, N., Jamjoom, M., & Al-Antari, M. (2023). Pre-trained transformer-based models for text classification using low-resourced Ewe language. Systems, 12(1), Article 1. https://doi.org/10.3390/systems12010001
Akl, H. (2024). DSTI at LLMs4OL 2024 Task A: Intrinsic versus extrinsic knowledge for type classification. arXiv. https://doi.org/10.48550/arXiv.2408.14236
Bouchachi, M., Jiménez-Delgado, A., De Gracia-Soriano, P., & Nemroudi, R. (2025). Architectural heritage and artificial intelligence: Diagnosis and solutions proposed by ChatGPT for Algerian historical monuments. Heritage, 8(4), Article 139. https://doi.org/10.3390/heritage8040139
Caramiaux, B. (2023). AI with museums and cultural heritage. In AI in Museums (pp. 117–130). transcript Verlag. https://doi.org/10.14361/9783839467107
Casillo, M., Clarizia, F., D’Aniello, G., De Santo, M., Lombardi, M., & Santaniello, D. (2020). CHAT-Bot: A cultural heritage aware teller-bot for supporting touristic experiences. Pattern Recognition Letters, 131, 234–243. https://doi.org/10.1016/j.patrec.2020.01.003
Casillo, M., De Santo, M., Mosca, R., & Santaniello, D. (2022). An ontology-based chatbot to enhance experiential learning in a cultural heritage scenario. Frontiers in Artificial Intelligence, 5, Article 808281. https://doi.org/10.3389/frai.2022.808281
Danopoulos, D., Kachris, C., & Soudris, D. (2019). Approximate similarity search with FAISS framework using FPGAs on the cloud. In Embedded Computer Systems: Architectures, Modeling, and Simulation (pp. 373–386). Springer. https://doi.org/10.1007/978-3-030-27562-4_27
Fabbri, F., Collina, F., & Barzaghi, S. (2023). AI and chatbots as a storytelling tool to personalize the visitor experience: The case of National Museum of Ravenna [Conference poster]. ExICE 2023: Extended Intelligence for Cultural Engagement, Bologna, Italy. Zenodo. https://doi.org/10.5281/zenodo.7973638
Fu, Q. Y., Dong, S. H., & Yuan, C. H. (2025). The current status and challenges of artificial intelligence in the digital preservation of cultural heritage. Journal of Artificial Intelligence & Robotics, 2(1), Article 1018. https://doi.org/10.52768/3067-7947/1018
Hamm, P., & Klesel, M. (2021). Success factors for the adoption of artificial intelligence in organizations: A literature review. In AMCIS 2021 Proceedings. Association for Information Systems. https://aisel.aisnet.org/amcis2021/art_intel_sem_tech_intelligent_systems/art_intel_sem_tech_intelligent_systems/10
Mallouhy, R., Fallatah, K., & Alkhateeb, M. (2025). RAG-driven AI for architectural heritage management: Optimizing renovation and preservation of Saudi traditional identity. In Dakam’s spring 2025 architecture and urban design conferences proceedings (pp. 131–141). Dakam Books. https://www.dakamconferences.org/_files/ugd/bac820_d171ab8323a24697b44b78c8a0e7129d.pdf
Nafis, F., Yahyaouy, A., & Aghoutane, B. (2022). Chatbots for cultural heritage: A real added value. In Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning (BML) (Vol. 1, pp. 502–506). SciTePress. https://doi.org/10.5220/0010737700003101
Natale, S., Surace, B., Mensa, E., & Befera, L. (2025). ChatGPT for cultural heritage and the customization of generative AI: A talkthrough analysis of the Luigi Einaudi chatbot. New Media & Society. Advance online publication. https://doi.org/10.1177/14614448251384258
Panda, M. (2025). Agentic RAG: Redefining retrieval-augmented generation for adaptive intelligence. International Research Journal of Engineering and Technology, 12(1), 731–739. https://www.irjet.net/volume12-issue01
Peng, Y., Heyn, H., & Horkoff, J. (2025). Data challenges in AI systems and their solutions: A requirements and AI engineering systematic literature review and comparison [Preprint]. Research Square. https://doi.org/10.21203/rs.3.rs-8077403/v1
Rachabatuni, P. K., Principi, F., Mazzanti, P., & Bertini, M. (2024). Context-aware chatbot using MLLMs for cultural heritage. In Proceedings of the 15th ACM Multimedia Systems Conference (pp. 459–463). https://doi.org/10.1145/3625468.3652193
Robertson, S., & Zaragoza, H. (2009). The probabilistic relevance framework: BM25 and beyond. Foundations and Trends in Information Retrieval, 3(4), 333–389. https://doi.org/10.1561/1500000019
Sathiyabamavathy, K., & Anju, K. (2024). Role of chatbots in cultural heritage tourism: An empirical study on ancient forts and palaces. Journal of Heritage Management, 9, 9–28. https://doi.org/10.1177/24559296241253932
Sinha, S., & Lee, Y. (2024). Challenges with developing and deploying AI models and applications in industrial systems. Discover Artificial Intelligence, 4, Article 55. https://doi.org/10.1007/s44163-024-00151-2
Tatić, D., Stanković, R., & Goynov, M. (2025). Usage of geospatial augmented reality for the representation of national heritage. Digital Presentation and Preservation of Cultural and Scientific Heritage, 15, 99–106. https://doi.org/10.55630/dipp.2025.15.9
Tian, L., & Jiang, N. (2024). Research on detection methods for text generated by large language models based on multi-model ensemble. Applied and Computational Engineering, 106, 59–67. https://doi.org/10.54254/2755-2721/106/20241331
Wang, L., Chen, S., Jiang, L., Pan, S., Cai, R., Yang, S., & Yang, F. (2025). Parameter-efficient fine-tuning in large language models: A survey of methodologies. Artificial Intelligence Review, 58, Article 227. https://doi.org/10.1007/s10462-025-11236-4
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Digital Presentation and Preservation of Cultural and Scientific Heritage
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
