"The Diagram is like Guardrails": Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representation

2025-03-21

AI Summary

This paper addresses the limited intelligent assistance provided by current AI tools for conceptual data analysis tasks—particularly hypothesis generation. We propose a human-AI collaborative interface that employs an ordered node-link tree as a structured “guardrail,” embedding AI-generated textual and visual prompts directly within the visual exploration workflow. This design establishes a shared representational space for hypothesis exploration, facilitating the translation from abstract conceptualization to data-driven insights. Innovatively, the node-link diagram serves as a constraint mechanism that supports both parallel exploration and iterative refinement, enabling global overviews and efficient backtracking while preserving workflow structure. A user study (n=22) demonstrates that participants generated an average of 21.82 hypotheses; AI-provided visualization prompts significantly reduced cognitive load and enhanced the data grounding, depth, and breadth of hypothesis exploration.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Data Mining & Knowledge Management: Data Visualization & Summarization
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Web data visualization
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Data analysis encompasses a spectrum of tasks, from high-level conceptual reasoning to lower-level execution. While AI-powered tools increasingly support execution tasks, there remains a need for intelligent assistance in conceptual tasks. This paper investigates the design of an ordered node-link tree interface augmented with AI-generated information hints and visualizations, as a potential shared representation for hypothesis exploration. Through a design probe (n=22), participants generated diagrams averaging 21.82 hypotheses. Our findings showed that the node-link diagram acts as"guardrails"for hypothesis exploration, facilitating structured workflows, providing comprehensive overviews, and enabling efficient backtracking. The AI-generated information hints, particularly visualizations, aided users in transforming abstract ideas into data-backed concepts while reducing cognitive load. We further discuss how node-link diagrams can support both parallel exploration and iterative refinement in hypothesis formulation, potentially enhancing the breadth and depth of human-AI collaborative data analysis.

Problem

• Designing AI-augmented node-link diagrams for hypothesis exploration
• Enhancing conceptual reasoning in data analysis with AI assistance
• Reducing cognitive load through AI-generated visual hints

Innovation

• AI-augmented node-link tree interface
• Interactive shared representation for hypotheses
• Visual hints reduce cognitive load