Author ORCID
0000-0002-8326-8568
Date of this Version
3-2025
Document Type
Presentation
Abstract
This presentation shares a pilot study to assess the multimodal AI tool LLaVA (Large Language and Vision Assistant) in generating descriptive metadata for digitized photographs. The study focuses on evaluation methods for AI-generated descriptions utilizing structured rubrics, which will assess the accuracy, bias, usability, and overall effectiveness of the AI tool. The presentation will also cover the ethics and best practices of using AI-generated metadata for sensitive content. Attendees will gain insights into practical methods for critically evaluating AI-generated outputs, equipping them with adaptable, relevant assessment techniques that may be useful in various library workflow settings.
Recommended Citation
Bakker, Rebecca and Ferreiro, Adaleen, "The Metadata is LLaVA: Evaluating Generative AI for Digital Records" (2025). Works of the FIU Libraries. 162.
https://digitalcommons.fiu.edu/glworks/162
Rights Statement
In Copyright - Educational Use Permitted. URI: http://rightsstatements.org/vocab/InC-EDU/1.0/
This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. In addition, no permission is required from the rights-holder(s) for educational uses. For other uses, you need to obtain permission from the rights-holder(s).