Skip to content

A design-oriented pedagogical framework for integrating LLMs to scaffold critical thinking in higher education

Design · All designs
Evidence · no claims cited

Description

The article proposes a normative, design-oriented framework grounded in Design-Based Research, instructional-design theory, AI ethics and Freirean critical pedagogy. It links three risks of unstructured LLM use to six intellectual processes and eight design principles, arguing that 'the value of generative AI in education is not technical but fundamentally pedagogical'. It positions LLMs as objects of inquiry learners must interrogate rather than as tutors or efficiency supports.

Design Implications

Context

Requirements

  • Requires deliberate instructional sequencing and alignment of principles with the cognitive, metacognitive and epistemic processes they support

Constraints

  • The authors state the framework 'is not intended as a definitive or universal solution, but as provisional pedagogical orientation that must remain open to critique, adaptation, and contextual interpretation'

Target Learners

  • higher education students

Learning Goals

  • critical thinking
  • epistemic agency
  • metacognitive regulation

Claims

Examples

-

Key Sources

  • Mireia Vendrell, Samantha-Kaye Johnston. (2026). Scaffolding critical thinking with generative AI: Design principles for integrating large language models in higher education. Computers and Education: Artificial Intelligence. https://doi.org/10.1016/j.caeai.2026.100572
Page metadata
Field Value
type design
id llm-critical-thinking-pedagogical-framework
title A design-oriented pedagogical framework for integrating LLMs to scaffold critical thinking in higher education
description The article proposes a normative, design-oriented framework grounded in Design-Based Research, instructional-design theory, AI ethics and Freirean critical pedagogy.
status review
generated by process:settle-candidates on 2026-10-12
trust unverified — no one has confirmed this page's content
sources 1 — mireia-vendrell-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.