Inquiry-based learning patterns in large language model-driven learning environments: An exploratory study from Bloom’s perspective

Abstract

Inquiry-based learning (IBL) is a problem-driven and exploration-centred learning method. The emergence of large language models (LLMs) such as ChatGPT provides a new interactive environment for IBL. However, research has not sufficiently explored how students interact with LLMs for IBL. This study aimed to understand students’ behaviours interacting with LLM at different cognitive levels during the IBL process. We conducted an experiment on a data science academic writing task and used Bloom’s educational taxonomy to examine the behavioural patterns of students’ IBL at different cognitive stages. Through the exploratory thematic analysis of 117 interview transcripts, 370 interaction records and 1,694 minutes of screen recordings, we identified 14 interaction patterns among students at different levels of prior knowledge. This article discusses the potential impact of self-efficacy and metacognitive monitoring on students’ learning behaviour in an LLM-driven learning environment and called for the design of a guiding planning framework and scaffolding to address challenges such as reliance on artificial intelligence. Our study provides new insights for the development of IBL in the era of emerging artificial intelligence technologies.

Implications for practice or policy:

• Educators can improve student inquiry-based learning outcomes by designing cognitive scaffolding that targets specific higher-order thinking stages.
• Instructional designers should develop planning frameworks that mitigate over-reliance on artificial intelligence while fostering student metacognitive monitoring.
• Policymakers could implement training programmes to enhance students' critical evaluation skills within an LLM-driven environment.