Reflections on evaluating the utility of an LLM for keywording health research
Journal of EAHIL · 15.06.2026 · 22 (2) · 18-23
DOI: 10.32384/jeahil22724 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of EAHIL, online erschienen am 15.06.2026. Verfasst von Claire Stansfield und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Generative artificial intelligence shows promise for rapidly annotating collections of research at scale. We reflected on our experiences of evaluating the ability of a Large Language Model (LLM) to apply predefined keywords to records of health research in the context of an evidence repository on vaccine research and research registers of health promotion effectiveness. Five aspects of evaluation helped us articulate key considerations and challenges across the use cases: 1) cyclical prompt development, 2) data availability and quality, 3) performance benchmarks and expectations, 4) task complexity and perspective and 5) workflows and tools.
Zitieren
APA
Stansfield, C., & Mutlu, A. F. (2026). Reflections on evaluating the utility of an LLM for keywording health research. Journal of EAHIL, 22(2), 18-23. https://doi.org/10.32384/jeahil22724
Vancouver
Stansfield C, Mutlu AF. Reflections on evaluating the utility of an LLM for keywording health research. Journal of EAHIL. 2026;22(2):18-23. doi:10.32384/jeahil22724
BibTeX
@article{Stansfield2026,
author = {Stansfield, Claire and Mutlu, Ailbhe Finnerty},
title = {Reflections on evaluating the utility of an LLM for keywording health research},
journal = {Journal of EAHIL},
year = {2026},
volume = {22},
number = {2},
pages = {18--23},
doi = {10.32384/jeahil22724}
}
EUVIMED