Designing Scaffolding Cards to Facilitate LLM-Based Socratic Instruction: An Exploratory Study of Response Strategies to Support Learning
Lujin Mao, Linyuan Dong, Wenan Li, Xiangen Hu, Kun-Pyo Lee, Zhibin Zhou
Abstract
The overreliance on large language models (LLMs)-generated answers poses risks to the development of learners’ critical thinking. Socratic instruction, which follows “tutor asks, student answers” approach, could mitigate overreliance by engaging learners with LLM-generated questions rather than passively seeking answers from LLMs. However, learners without effective response strategies often produce superficial answers and therefore undermine Socratic instruction. To bridge the gap, we first conducted a formative study (N=20) to analyze learners’ dialogue logs and interviews, deriving 18 Scaffolding Cards as response strategies to guide learners in framing their answers. A subsequent mixed-methods study (N=34) demonstrated that Scaffolding Cards improved critical thinking, optimized cognitive load allocation, and increased learning satisfaction compared to that without scaffolds. Our work reconfigures scaffolding by incorporating state-aware, agency-preserving, and function-transparent support. We further provide actionable implications for designing responsive and personalized scaffolding to facilitate learner-LLM interaction, introducing innovative perspectives for reclaiming learner agency in LLM-driven education.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Related papers
- Exploring Teacher-Chatbot Interaction and Affect in Block-Based ProgrammingBahare Riahi, Ally Limke, Xiaoyi Tian, Viktoriia Storozhevykh et al.CHI 2026 · 2 citations
- From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement LearningDavid Dinucu-Jianu, Jakub Macina, Nico Daheim, Ido Hakimi et al.EMNLP 2025
- Automatic Generation of Socratic Subquestions for Teaching Math Word ProblemsKumar Shridhar, Jakub Macina, Mennatallah El-Assady, Tanmay Sinha et al.EMNLP 2022 · 31 citations
- "Here the GPT made a choice, and every choice can be biased": How Students Critically Engage with LLMs through End-User Auditing ActivitySnehal Prabhudesai, Ananya Prashant Kasi, Anmol Mansingh, Anindya Das Antar et al.CHI 2025 · 15 citations
- Planning-Guided Tutoring with Assessment-Driven Memory for Pedagogical LLM TutorsZechen Li, Qiannan Zhu, Mei Wang, Jia Li et al.ACL 2026
