Designing for Collaboration: Visualization to Enable Human–LLM Analytical Partnership
IEEE Computer Graphics and Applications · 2025-09 · 45 (5) · 107-116
DOI: 10.1109/mcg.2025.3583451 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Computer Graphics and Applications, 2025-09. Verfasst von Mai Elshehaly und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 10 Literaturangaben. Gefördert von: Federal Ministry of Education and Research of Germany, North-Rhine Westphalia as part of the Lamarr Institute for Machine Learning and Artificial Intelligence, EU.
Abstract (Originalsprache)
Visualization artifacts have long served as anchors for collaboration and knowledge transfer in data analysis. While effective for human-human collaboration, little is known about their role in capturing and externalizing knowledge when working with large language models (LLMs). Despite the growing role of LLMs in analytics, their linear text-based workflows limit the ability to structure artifacts into useful and traceable representations of the analytical process. We argue that dynamic visual representations of evolving analysis-organizing artifacts and provenance into semantic structures, such as idea development and shifts in inquiry-are critical for effective human-LLM workflows. We demonstrate the current opportunities and limitations of using LLMs to track, structure, and visualize analytic processes, and propose a research agenda to leverage rapid advances in LLM capabilities. Our goal is to present a compelling argument for maximizing the role of visualization as a catalyst for more structured, transparent, and insightful human-LLM analytical interactions.
Förderung
- Federal Ministry of Education and Research of Germany
- North-Rhine Westphalia as part of the Lamarr Institute for Machine Learning and Artificial Intelligence
- EU
Zitieren
APA
Elshehaly, M., Jianu, R., Slingsby, A., Andrienko, G., Andrienko, N., & Rhyne, T. M. (2025). Designing for Collaboration: Visualization to Enable Human–LLM Analytical Partnership. IEEE Computer Graphics and Applications, 45(5), 107-116. https://doi.org/10.1109/mcg.2025.3583451
Vancouver
Elshehaly M, Jianu R, Slingsby A, Andrienko G, Andrienko N, Rhyne TM. Designing for Collaboration: Visualization to Enable Human–LLM Analytical Partnership. IEEE Computer Graphics and Applications. 2025;45(5):107-116. doi:10.1109/mcg.2025.3583451
BibTeX
@article{Elshehaly2025,
author = {Elshehaly, Mai and Jianu, Radu and Slingsby, Aidan and Andrienko, Gennady and Andrienko, Natalia and Rhyne, Theresa-Marie},
title = {Designing for Collaboration: Visualization to Enable Human–LLM Analytical Partnership},
journal = {IEEE Computer Graphics and Applications},
year = {2025},
volume = {45},
number = {5},
pages = {107--116},
doi = {10.1109/mcg.2025.3583451}
}
EUVIMED