Intelligent Drill-Down: Large Language Model-Driven Drill-Down Technique for Human-AI Collaborative Visual Exploration

2026-04-18

AI Summary

This work addresses the challenge of navigational disorientation and reduced exploration efficiency in multidimensional data visualization, where vast drill-down spaces overwhelm analysts. The paper proposes the first intelligent drill-down framework integrating large language models (LLMs) to interpret user interaction patterns, infer analytical intent, and generate high-value drill paths. To support parallel exploration, the system incorporates a branch management mechanism that enables users to maintain and switch between multiple exploration threads. Combining greedy algorithm-based approximate training with a hierarchical navigation interface, the framework facilitates human-AI collaborative, interactive insight discovery. Experimental results demonstrate that the approach significantly reduces users’ cognitive load while enhancing both exploration efficiency and the quality of insights derived from complex datasets.

Technology Category

• Data Mining & Knowledge Management: Intelligent Query Processing
• Humans and AI: Intelligent User Interfaces
• Intelligent Robots: Multi-Robot Systems

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Web data visualization

Abstract

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.

Problem

• drill-down
• visual analytics
• large language model
• human-AI collaboration
• multidimensional data

Innovation

• Intelligent Drill-Down
• Large Language Model
• Visual Analytics
• User Intent Inference
• Drill-Down Path Recommendation