Performance of a Small Language Model Versus a Large Language Model in Answering Glaucoma Frequently Asked Patient Questions: Development and Usability Study
Both models generated accurate content, but the answers were considered challenging for the average layperson to understand, making them unsuitable for health care-related information. Given the specialized SLM's comparable performance to the LLM, its high customization potential, lower cost, and ability to operate locally, it presents a viable option for deploying natural language processing in real-world ophthalmology clinical settings.
Authors
- Douglas Santos Costa (ORCID: https://orcid.org/0000-0002-3741-7892)
- Alessandro A. Jammal (ORCID: https://orcid.org/0000-0001-5341-8353)
- R. Muralidhar
- Luiz Arthur F. Beniz (ORCID: https://orcid.org/0000-0002-3230-5365)
- Marcus Guerreiro-Filho (ORCID: https://orcid.org/0000-0002-4683-5519)
- Adriano Cypriano Faneli (ORCID: https://orcid.org/0000-0001-8834-2600)
- Verônica Vilasboas-Campos
- Rafael Scherer
- Felipe A Medeiros
Institutions
- Miami Transplant Institute (US)
- Universidade Federal de São Paulo (BR)
Publication Details
- Journal
- JMIR AI
- Published
- 2026-01-06
- DOI
- https://doi.org/10.2196/72101
- Citations
- 1
- Primary Topic
- Health Literacy and Information Accessibility
- Type
- article
- Field-Weighted Citation Impact
- 46.02