EUVIMEDEUVIMED entdecken
Crossref

MatSci-YAMZ: Integrating Human and Artificial Intelligence Vocabulary

Scott McClellan, Addison Ireland, Colton Gerber, Joel Pepper, Christopher B. Rauch, Mat Kelly, John Kunze, Jane Greenberg

Data Science Journal · 13.07.2026 · 25

DOI: 10.5334/dsj-2026-023 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data Science Journal, erschienen am 13.07.2026. Verfasst von Scott McClellan und 7 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents MatSci-YAMZ, a novel implementation of Yet Another Metadata Zoo (YAMZ), a crowdsourced vocabulary application. MatSci-YAMZ is designed to assist vocabulary development for materials science by configuring a large language model (LLM) and provenance tracking into the YAMZ workflow. Implementation of MatSci-YAMZ occurred in three phases: requirements and model selection, development, and fine-tuning. The application utilizes the Gemma3:27b LLM to formulate definitions based upon examples provided with human definitions. Provenance tracking captures the evolution of LLM-generated definition evolution, which occurs in response to user comments. MatSci-YAMZ can improve shared semantics among communities of materials researchers whose terminology may contain nuances or idiosyncratic usages. Improved semantic alignment supports more concise data descriptions and use of metadata, which is foundational to supporting the FAIR principles of findability, accessibility, interoperability, and reusability. Improved provenance tracking also provides greater insight into how researchers engage with LLM-generated definitions as well as the changes that occur. MatSci-YAMZ opens several avenues of research into crowdsourced vocabulary development among materials researchers. Current findings highlight the need for additional user testing and study to better understand human-in-the-loop vocabulary development with existing LLMs.

Zitieren

APA

McClellan, S., Ireland, A., Gerber, C., Pepper, J., Rauch, C. B., Kelly, M., Kunze, J., & Greenberg, J. (2026). MatSci-YAMZ: Integrating Human and Artificial Intelligence Vocabulary. Data Science Journal, 25. https://doi.org/10.5334/dsj-2026-023

Vancouver

McClellan S, Ireland A, Gerber C, Pepper J, Rauch CB, Kelly M, et al. MatSci-YAMZ: Integrating Human and Artificial Intelligence Vocabulary. Data Science Journal. 2026;25. doi:10.5334/dsj-2026-023

BibTeX
@article{McClellan2026,
  author = {McClellan, Scott and Ireland, Addison and Gerber, Colton and Pepper, Joel and Rauch, Christopher B. and Kelly, Mat and Kunze, John and Greenberg, Jane},
  title = {MatSci-YAMZ: Integrating Human and Artificial Intelligence Vocabulary},
  journal = {Data Science Journal},
  year = {2026},
  volume = {25},
  doi = {10.5334/dsj-2026-023}
}
Kostenlos starten →