Mindalogue: LLM-Powered Nonlinear Interaction for Effective Learning and Task Exploration

TL;DR

Mindalogue introduces a non-linear interaction system for large language models, reducing cognitive load and enhancing user understanding in complex tasks through a structured 'nodes + canvas' approach.

Contribution

This work presents a novel non-linear interaction model for LLMs, improving efficiency and user control compared to traditional linear methods.

Findings

Reduced task steps in complex information processing

Improved user comprehension of complex data

Enhanced user efficiency and freedom

Abstract

Current generative AI models like ChatGPT, Claude, and Gemini are widely used for knowledge dissemination, task decomposition, and creative thinking. However, their linear interaction methods often force users to repeatedly compare and copy contextual information when handling complex tasks, increasing cognitive load and operational costs. Moreover, the ambiguity in model responses requires users to refine and simplify the information further. To address these issues, we developed "Mindalogue", a system using a non-linear interaction model based on "nodes + canvas" to enhance user efficiency and freedom while generating structured responses. A formative study with 11 users informed the design of Mindalogue, which was then evaluated through a study with 16 participants. The results showed that Mindalogue significantly reduced task steps and improved users' comprehension of complex information. This study highlights the potential of non-linear interaction in improving AI tool efficiency and user experience in the HCI field.