Mind-Mapping Data Analysis with LLMs: From Vision to First Steps
We explore how large language models (LLMs) can support real-time visual mapping of data analysis workflows. Building on an earlier vision, we investigate if and how LLMs can decompose analytic dialogues into “analysis maps“ that capture key semantic units such as questions, datasets, tasks, and findings. Using two exemplar analyses, we test both post-hoc and interactive strategies for generating these maps and experiment with prompting techniques for structuring and updating them. Results, documented in Observable notebooks, suggest that LLMs can scaffold analysis-as-network meaningfully-laying the groundwork for user-facing systems and moving beyond purely textual forms of LLM-mediated analysis.
- Veröffentlicht in:
Computer Graphics and Visual Computing (CGVC) - Typ:
Article - Autoren:
- Jahr:
2025 - Source:
https://diglib.eg.org/items/5cc46cf2-1edd-48b5-ad73-35ae8c8bdeb1
Informationen zur Zitierung
: Mind-Mapping Data Analysis with LLMs: From Vision to First Steps, Computer Graphics and Visual Computing (CGVC), 2025, https://diglib.eg.org/items/5cc46cf2-1edd-48b5-ad73-35ae8c8bdeb1, Jianu.etal.2025a,
@Article{Jianu.etal.2025a,
author={Jianu, Radu; Hutchinson, Maeve; Andrienko, Natalia; Andrienko, Gennady; Elshehaly, Mai; Slingsby, Aidan},
title={Mind-Mapping Data Analysis with LLMs: From Vision to First Steps},
journal={Computer Graphics and Visual Computing (CGVC)},
url={https://diglib.eg.org/items/5cc46cf2-1edd-48b5-ad73-35ae8c8bdeb1},
year={2025},
abstract={We explore how large language models (LLMs) can support real-time visual mapping of data analysis workflows. Building on an earlier vision, we investigate if and how LLMs can decompose analytic dialogues into “analysis maps“ that capture key semantic units such as questions, datasets, tasks, and findings. Using two exemplar analyses, we test both post-hoc and interactive strategies...}}
