Intelligent Drill-Down: Large Language Model-Driven Drill-Down Technique for Human-AI Collaborative Visual Exploration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913042582732800 |
|---|---|
| author | Zheng, Zhijun Qiu, Tian Zhao, Yuheng Chen, Siming |
| author_facet | Zheng, Zhijun Qiu, Tian Zhao, Yuheng Chen, Siming |
| contents | In visual analytics, applying filters to drill-down and extract higher-value insights is a common and important data analysis method. When the drill-down space becomes excessively large, analysts may lose orientation, leading to decreased efficiency in the drill-down process. To tackle these challenges, we propose the Intelligent Drill-Down Framework, in which a large language model (LLM) facilitates the generation of visual insights, leverages user interaction data to interpret user intent, and generates appropriate drill-down paths. Our method is designed to assist users in identifying valuable drill-down paths when exploring multidimensional data, thereby reducing the cognitive burden of data interpretation and facilitating the generation of insights. Specifically, we propose a drill-down path recommendation method, in which the LLM is trained to approximate a validated greedy algorithm. Secondly, we analyze the user's intent to construct a drill-down chart. Finally, we design a branch management method. Building upon this framework, we designed a system that includes a hybrid interface providing hierarchical navigation to monitor users and manage parallel branches, a visualization panel for interactive data exploration, and an insight panel to present analytical findings and generate drill-down recommendations. We evaluated the effectiveness of our method through a demonstrative use case and a user study. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17002 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Intelligent Drill-Down: Large Language Model-Driven Drill-Down Technique for Human-AI Collaborative Visual Exploration Zheng, Zhijun Qiu, Tian Zhao, Yuheng Chen, Siming Human-Computer Interaction In visual analytics, applying filters to drill-down and extract higher-value insights is a common and important data analysis method. When the drill-down space becomes excessively large, analysts may lose orientation, leading to decreased efficiency in the drill-down process. To tackle these challenges, we propose the Intelligent Drill-Down Framework, in which a large language model (LLM) facilitates the generation of visual insights, leverages user interaction data to interpret user intent, and generates appropriate drill-down paths. Our method is designed to assist users in identifying valuable drill-down paths when exploring multidimensional data, thereby reducing the cognitive burden of data interpretation and facilitating the generation of insights. Specifically, we propose a drill-down path recommendation method, in which the LLM is trained to approximate a validated greedy algorithm. Secondly, we analyze the user's intent to construct a drill-down chart. Finally, we design a branch management method. Building upon this framework, we designed a system that includes a hybrid interface providing hierarchical navigation to monitor users and manage parallel branches, a visualization panel for interactive data exploration, and an insight panel to present analytical findings and generate drill-down recommendations. We evaluated the effectiveness of our method through a demonstrative use case and a user study. |
| title | Intelligent Drill-Down: Large Language Model-Driven Drill-Down Technique for Human-AI Collaborative Visual Exploration |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2604.17002 |