Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Passive Consumption to Active Interaction: Exploring Interactive LLM Scaffolding to Support Learning Engagement

Zixin Chen, Haotian Li, Zhe Liu, Huamin Qu, Xing Xie

TL;DR

This work explores whether embedding lightweight interactive components into LLM-generated scaffolding responses can promote learning-oriented engagement and improve short-term learning outcomes, and concludes with design implications for integrating interaction into LLM-generated scaffolding to support active learning engagement.

Abstract

Large Language Models (LLMs) are increasingly used as learning companions, providing scaffolded explanations, hints, or step-by-step guidance. However, in current LLM-based learning scenarios, scaffolded content is primarily consumed passively, offering limited support for active learner engagement. Learning science research suggests that effective educational scaffolding depends not only on what support is provided, but also on how learners engage with it. In this work, we explore whether embedding lightweight interactive components into LLM-generated scaffolding responses can promote learning-oriented engagement and improve short-term learning outcomes. We evaluated this approach through a within-subjects laboratory study (N=8). Results provide initial evidence that interactive scaffolding increases learners' perceived engagement and attentional focus, while supporting short-term learning performance. We conclude with design implications for integrating interaction into LLM-generated scaffolding to support active learning engagement.

From Passive Consumption to Active Interaction: Exploring Interactive LLM Scaffolding to Support Learning Engagement

TL;DR

This work explores whether embedding lightweight interactive components into LLM-generated scaffolding responses can promote learning-oriented engagement and improve short-term learning outcomes, and concludes with design implications for integrating interaction into LLM-generated scaffolding to support active learning engagement.

Abstract

Large Language Models (LLMs) are increasingly used as learning companions, providing scaffolded explanations, hints, or step-by-step guidance. However, in current LLM-based learning scenarios, scaffolded content is primarily consumed passively, offering limited support for active learner engagement. Learning science research suggests that effective educational scaffolding depends not only on what support is provided, but also on how learners engage with it. In this work, we explore whether embedding lightweight interactive components into LLM-generated scaffolding responses can promote learning-oriented engagement and improve short-term learning outcomes. We evaluated this approach through a within-subjects laboratory study (N=8). Results provide initial evidence that interactive scaffolding increases learners' perceived engagement and attentional focus, while supporting short-term learning performance. We conclude with design implications for integrating interaction into LLM-generated scaffolding to support active learning engagement.
Paper Structure (7 sections, 3 figures)

This paper contains 7 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Methods
  3. Prototype Design
  4. Experimental Design
  5. Findings
  6. Design Insights from Think-Aloud Interview Study
  7. Conclusion

Figures (3)

  • Figure 1: Overview of the LLM-based tutoring prototype. (A) The Learning Material Zone presents the target proof and allows learners to select the scaffolding condition. (B) The Chatbot Tutor Zone supports question-driven interaction with the LLM; scaffolded content is revealed via scratch-off interaction in the interactive condition and shown as plain text in the non-interactive condition.
  • Figure 2: (A) NASA-TLX workload ratings across conditions. (B) Proof comprehension quiz performance across conditions and number of questions asked during the learning phase. (C) Perceived helpfulness and engagement of interactive scaffolding (7-point Likert).
  • Figure 3: Interaction design ideas proposed by participants during the think-aloud brainstorming. Designs are analyzed and organized by scaffolding means, illustrating how different interaction forms align with distinct pedagogical roles of scaffolding.