It Takes a Village

A Distributed Training Model for AI-Based Chatbots

Authors

DOI:

https://doi.org/10.5860/ital.v43i3.17243

Keywords:

AI, Chatbots, artificial intelligence, modern library services, technology acceptance model, tam, perceived usefulness, perceived ease of use, chatbase

Abstract

The introduction of Large Language Models (LLM) to the chatbot landscape has opened intriguing possibilities for academic libraries to offer more responsive and institutionally contextualized support to users, especially outside of regular service hours. While a few academic libraries currently employ AI-based chatbots on their websites, this service has not yet become the norm and there are no best practices in place for how academic libraries should launch, train, and assess the usefulness of a chatbot. In summer 2023, staff from the University of Delaware’s Morris Library information technology (IT) and reference departments came together in a unique partnership to pilot a low-cost AI-powered chatbot called UDStax. The goals of the pilot were to learn more about the campus community’s interest in engaging with this tool and to better understand the labor required on the staff side to maintain the bot. After researching six different options, the team selected Chatbase, a subscription-model product based on ChatGPT 3.5 that provides user-friendly training methods for an AI model using website URLs and uploaded source material. Chatbase removed the need to utilize the OpenAI API directly to code processes for submitting information to the AI engine to train the model, cutting down the amount of work for library information technology and making it possible to leverage the expertise of reference librarians and other public-facing staff, including student workers, to distribute the work of developing, refining, and reviewing training materials. This article will discuss the development of prompts, leveraging of existing data sources for training materials, and workflows involved in the pilot. It will argue that, when implementing AI-based tools in the academic library, involving staff from across the organization is essential to ensure buy-in and success. Although chatbots are designed to hide the effort of the people behind them, that labor is substantial and needs to be recognized.

Author Biographies

Beth Twomey, University of Delaware

Head, Research and Engagement

Annie Johnson, University of Delaware

Associate University Librarian for Publishing, Preservation, Research and Digital Access

Colleen Estes, University of Delaware

Coordinator, Web Support and Development

References

Abby S. Kasowitz, “Trends and Issues in Digital Reference Services,” ERIC Digest (2001), https://eric.ed.gov/?id=ED457869.

Aditi Bandyopadhyay and Mary Kate Boyd-Byrnes, “Is the Need for Mediated Reference Service in Academic Libraries Fading Away in the Digital Environment?,” Reference Services Review 44, no. 4 (2016): 596–626.

Danielle Kane, “Analyzing an Interactive Chatbot and Its Impact on Academic Reference Services,” ARL 2019 Recasting the Narrative (2019), http://hdl.handle.net/11213/17624.

Deanne Allison, “Chatbots in the Library: Is it Time?,” Library Hi Tech 30, no. 1 (March 2012)

Diane Nester Kresh, “Offering High Quality Service on the Web: The Collaborative Digital Reference Service,”DiLib Magazine 6, no. 6 (June 2002), http://www.doi.org/10.1045/june2000-kresh.

Majideh Sanji, Hassan Behzadi, and Gisu Gomroki, “Chatbot: An Intelligent Tool for Libraries,” Library Hi Tech News 3 (2022): 17–19.

Michelle Ehrenpreis and J. DeLooper, “Implementing a Chatbot on a Library Website,” Journal of Web Librarianship 16, no. 2 (2022): 120–42.

Scott Carlson, “Reference Questions Without Visiting the Library,” The Chronicle of Higher Education (May 31, 2002), https://www.chronicle.com/article/new-service-allows-the-public-to-pose-reference-questions-without-visiting-the-library/?sra=true.

Sharesly Rodriguez and Christina Mune, “Library Chatbots: Easier Than You Think,” Computers in Libraries 41, no. 8 (2021).

Sharesly Rodriguez and Christina Mune, “Uncoding Library Chatbots: Deploying a New Virtual Reference Tool at the San Jose State University Library,” Reference Services Review 50 no. 3/4 (2022): 392–405.

Shu Wan, “Developing an Engati-Based Library Chatbot to Improve Reference Services,” in Innovation and Experiential Learning in Academic Libraries: Meeting the Needs of Today's Students, ed. S. Nagle and E. Tzoc (Rowman and Littlefield, 2022): 190.

T. Richards-Resendes, “Springshare Announces LibAnswers Chatbot,” Springshare, February 15, 2023, https://blog.springshare.com/2023/02/15/springshare-announces-libanswers-chatbot/.

Yrjo Lappalainen and Nikesh Narayanan, “Aisha: A Custom AI library Chatbot Using the ChatGPT API” Journal of Web Librarianship 17, no. 3 (2023): 37–58.

Downloads

Published

2024-09-23

How to Cite

Twomey, B., Johnson, A., & Estes, C. (2024). It Takes a Village: A Distributed Training Model for AI-Based Chatbots. Information Technology and Libraries, 43(3). https://doi.org/10.5860/ital.v43i3.17243

Issue

Section

Articles