Evaluating Node-tree Interfaces for AI Explainability
Lifei Wang, Natalie Friedman, Chengchao Zhu, Zeshu Zhu, S. Joy Mountford
TL;DR
This study addresses AI explainability and user trust in enterprise contexts by comparing a Node-tree hierarchical visualization interface with a traditional chatbot. Using a between-subjects design with 20 business users across North America and Europe, it assesses trust, task performance, and usability across four real-world-like tasks. Results indicate Node-tree enhances brainstorming, context retention, and perceived trust for complex tasks, whereas chatbots excel at linear, step-by-step processes; findings advocate for adaptive interfaces that switch presentation formats by task. The work provides actionable design guidance for human-AI interaction and enterprise decision-support tools, highlighting the potential for improved transparency and user confidence through structured visualizations paired with conversational capabilities.
Abstract
As large language models (LLMs) become ubiquitous in workplace tools and decision-making processes, ensuring explainability and fostering user trust are critical. Although advancements in LLM engineering continue, human-centered design is still catching up, particularly when it comes to embedding transparency and trust into AI interfaces. This study evaluates user experiences with two distinct AI interfaces - node-tree interfaces and chatbot interfaces - to assess their performance in exploratory, follow-up inquiry, decision-making, and problem-solving tasks. Our design-driven approach introduces a node-tree interface that visually structures AI-generated responses into hierarchically organized, interactive nodes, allowing users to navigate, refine, and follow up on complex information. In a comparative study with n=20 business users, we observed that while the chatbot interface effectively supports linear, step-by-step queries, it is the node-tree interface that enhances brainstorming. Quantitative and qualitative findings indicate that node-tree interfaces not only improve task performance and decision-making support but also promote higher levels of user trust by preserving context. Our findings suggest that adaptive AI interfaces capable of switching between structured visualizations and conversational formats based on task requirements can significantly enhance transparency and user confidence in AI-powered systems. This work contributes actionable insights to the fields of human-robot interaction and AI design, particularly for enterprise applications where trust-building is critical for teams.