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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Rui, Zhang, Ziyao, Zhu, Fengliang, Zhou, Jiajie, Rao, Anyi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909349497012224
author Zhang, Rui
Zhang, Ziyao
Zhu, Fengliang
Zhou, Jiajie
Rao, Anyi
author_facet Zhang, Rui
Zhang, Ziyao
Zhu, Fengliang
Zhou, Jiajie
Rao, Anyi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10570
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mindalogue: LLM-Powered Nonlinear Interaction for Effective Learning and Task Exploration
Zhang, Rui
Zhang, Ziyao
Zhu, Fengliang
Zhou, Jiajie
Rao, Anyi
Human-Computer Interaction
Systems and Control
68U35(Primary), 68T20(Secondary)
H.5.2
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.
title Mindalogue: LLM-Powered Nonlinear Interaction for Effective Learning and Task Exploration
topic Human-Computer Interaction
Systems and Control
68U35(Primary), 68T20(Secondary)
H.5.2
url https://arxiv.org/abs/2410.10570