Introduction

As the production of knowledge synthesis research accelerates in the field of exercise science, so has the proliferation of generative AI (genAI) academic search engines that claim to speed up the process of information retrieval—an often time-consuming and resource-intensive slog that requires specialized skills. These tools are potentially an attractive option for researchers looking to save time and resources, but it remains uncertain whether they can match the rigor of traditional search methods. Undermind is a genAI academic search engine that aims to help users “research with unprecedented breadth and depth” and uses iterative semantic search technology to search faster than a human without compromising thoroughness. This study asks: Does Undermind match or improve upon the real-world search practices reported in exercise science knowledge synthesis studies?

Methods

This study calculated the precision and recall of the academic AI search engine Undermind against a random sample of search methods reported in 50 systematic reviews published in exercise science journals between 2015-2020. Each review question was searched the same way twice in Undermind to assess replicability. An analysis was conducted to explore patterns in the performance of Undermind.

Results

Analysis is ongoing and results will be added.

Discussion & Conclusion to be added.

Panel Description Health librarians are increasingly authoring their own open educational resources (OERs) to teach advanced literature searching—an essential skill for evidence synthesis. These instructional materials are often created in response to gaps in existing resources and go beyond simple guides by incorporating bilingual content, scaffolded exercises, knowledge checks, and video tutorials. They reflect librarians’ deep expertise and commitment to affordable, open, and high-quality learning materials. This panel will highlight three librarian-led OER projects that exemplify this growing trend. Through brief presentations and a moderated discussion, panelists will share insights into the design, implementation, and impact of their work, and reflect on the broader implications of OER creation as a scholarly and pedagogical practice.

Panelists

• Sandra McKeown (Queen’s University) will present her self-paced module for teaching systematic review search strategies.
• Erica Nekolaichuk (University of Toronto) will discuss her comprehensive LibGuide for advanced health sciences searching.
• Peter Farrell (University of Ottawa) will share his and Nigèle Langlois’ bilingual adaptation of Erica’s guide, tailored to the uOttawa context.

Introduction:
In 2025, the creation of the RAISE (Responsible Use of Artificial Intelligence in Evidence Synthesis) guidelines signaled increased interest in exploring ethical use of artificial intelligence tools for improving sustainability in knowledge synthesis (KS) work. Over the last 3 years, there has been an increase in the development and availability of generative AI tools, including chatbots, AI academic search engines, and AI add-ons/assistants connected to traditional databases. As librarians who support KS, we were interested in finding out whether health librarians were using generative-AI tools in their KS practice, and if so, when and how.

Methods:
We used a cross-sectional survey for our study. Eligibility was restricted to librarians currently supporting at least one health sciences program, and involved in knowledge synthesis as a consultant, collaborator, or both. The survey included questions related to demographics and librarians’ use of generative AI tools in the context of their roles as educational consultants and collaborators.

Results: To be added

Discussion & Conclusion: To be added