2024 ACM/IEEE Joint Conference on Digital Libraries.

Workshop Description

In this workshop, participants will explore several demonstrations from the Liberating Libraries through Generative Artificial Intelligence (LIBRAI) initiative. A project funded by the Institute of Museum and Library Services aims to advance the integration of Generative AI technologies in university libraries. Virginia Tech and the University of California, Riverside, who collaborated on the initiative, address the challenge of limited AI adoption in libraries by providing training, resources, and workshops designed to empower library professionals. It focuses on enhancing AI literacy [1], improving operational efficiency, and fostering innovation in library settings. The workshop will showcase practical applications and solutions that participating libraries have implemented. Examples include using large language models to improve information provision services, personalize user experiences, and optimize resource discovery. Attendees will see how these models are fine-tuned, evaluated, and deployed and learn about the challenges and successes encountered during the process. Generative AI has been utilized successfully in various fields such as healthcare, finance, and education [2], suggesting potential for significant impacts in library services as well. Through case studies and interactive sessions, participants will gain hands-on experience using AI technologies to enhance library operations. Activities will involve learning to developing and fine-tuning AI models, implementing hallucination guardrails to increase reliability, and utilizing Retrieval-Augmented Generation (RAG) techniques to enhance the generation of information from unstructured data sources by incorporating relevant external content. The workshop will emphasize practical strategies for overcoming technical and operational barriers, equipping participants with the knowledge and skills they need to succeed in their AI integration journey [3].

Workshop Outline

1 Introduction

The workshop begins with an introduction to the LIBRAI project, setting the stage for exploring the potential of Generative AI in library environments. Facilitators will introduce the central research question: How can generative AI be utilized in libraries to streamline operations and elevate the quality of services provided? This question will guide the workshop's discussions and collaborative activities, focusing on practical applications that directly enhance library services and user experience.

2 Presentations and Experience Sharing

Facilitators and participants will share their experiences and research on AI integration in libraries, specifically focusing on using GPT-4 and Llama models [4]. Examples will include deploying these models for research purposes and other applications in library settings. Participants will discuss use cases such as improving search functionalities, enhancing catalog systems, and personalizing user experiences. An open discussion will follow, allowing participants to engage with each other’s work and provide feedback.

3 Discussion and Brainstorming Session

Participants will collaborate to identify common challenges and explore innovative solutions for AI integration. This interactive session will focus on addressing technical, ethical, and operational barriers to AI adoption. Small groups will work together to develop actionable strategies tailored to their library contexts. Each group will present their proposed solutions, fostering a wider discussion on best practices and innovative approaches.

4 Conclusion and Future Directions

The workshop will conclude by reviewing the key outcomes and actionable insights generated during the session. Facilitators will highlight successful strategies for integrating AI in libraries and guide discussions on potential research directions. Participants will be encouraged to explore collaborative projects that could advance the application of generative AI in libraries.

Opportunities for continued collaboration and networking will be emphasized, along with the importance of ongoing knowledge sharing. Facilitators will provide resources and tools to help participants further explore generative AI technologies. Participants will be encouraged to stay connected, fostering a community dedicated to innovation and excellence in library services.

Anticipated Audience

This workshop is tailored for scholars and professionals in digital libraries and information science, including those specializing in information management, digital services, and library technology. It is suitable for individuals interested in exploring the application of generative AI technologies within library environments and those seeking to enhance their understanding and use of large language models and large multimodal models.

Expected Outcomes

Participants will acquire a comprehensive understanding of integrating Generative AI into library environments to improve operational efficiency and service quality. The workshop aims to empower attendees with actionable strategies for AI adoption, enabling them to develop innovative solutions tailored to their specific library contexts. Through collaborative research discussions, participants will explore new directions for future exploration, helping to effectively address the central research question of utilizing generative AI to streamline operations and elevate library services.

Workshop Facilitators

	Yinlin Chen holds a Ph.D. in Computer Science and Applications from Virginia Tech, and a M.S. and a B.S. in Computer Science from National Tsing Hua University, Taiwan. He is an Assistant Director of the Center for Digital Research & Scholarship and an Assistant Professor at the Virginia Tech Libraries. His professional interests include Digital Libraries, Machine Learning, Artificial Intelligence, and Cloud Computing.
	Le Yang holds a Ph.D. in Library Science from Wuhan University. He is an Associate Vice Provost & University Librarian at University of Oregon and serves on editorial boards of Journal of Library Resource Sharing, College and Research Libraries, International Journal of Librarianship, and Journal of Web Librarianship. His research interests include digital librarianship, open repositories, open infrastructure, and data governance.
	Zhiwu Xie holds a Ph.D. in Mechanical Engineering from Shanghai Jiao Tong University. He is Assistant University Librarian for Research & Technology at University of California, Riverside. His research interests focus on library cyberinfrastructure, data management, digital preservation, and web archiving, with application areas ranging from biomed image processing, autonomous vehicle, ecological systems, to smart building.

REFERENCES

[1] Carroll, A. J., & Borycz, J. (2024). Integrating large language models and generative artificial intelligence tools into information literacy instruction. The Journal of Academic Librarianship, 50(4), 102899.

[2] Ooi, K. B., Tan, G. W. H., Al-Emran, M., Al-Sharafi, M. A., Capatina, A., Chakraborty, A., ... & Wong, L. W. (2023). The potential of generative artificial intelligence across disciplines: Perspectives and future directions. Journal of Computer Information Systems, 1-32.

[3] Raiaan, M. A. K., Mukta, M. S. H., Fatema, K., Fahad, N. M., Sakib, S., Mim, M. M. J., ... & Azam, S. (2024). A review on large Language Models: Architectures, applications, taxonomies, open issues and challenges. IEEE Access.

[4] Bsharat, S. M., Myrzakhan, A., & Shen, Z. (2023). Principled instructions are all you need for questioning llama-1/2, gpt-3.5/4. arXiv preprint arXiv:2312.16171.