Date
Publisher
arXiv
Prompt engineering is commonly presented as a technical competence for obtaining more accurate, relevant, or well-formatted outputs from large language models (LLMs). However, in STEM education, prompting should also be understood as a continuous epistemic practice. Students interpret contextual and disciplinary cues and adopt expectations about what kind of knowledge, representation, and action are appropriate. Drawing on epistemological framing, and AI-mediated concept-to-decision reasoning, the paper presents a new framework called epistemic prompting and proposes a multi-turn Framing-Prompting Loop. The educationally relevant outcome is a prompt framing trajectory: the sequence of prompts, model responses, learner uptake, disciplinary checks, and reframing moves through which a knowledge task develops. In this framework, an initial prompt establishes a provisional macro-frame by selecting the problem, representations, assumptions, criteria, and distribution of work between learner and model. Each subsequent learner turn can then maintain, specify, challenge, repair, or transform that organization. The implications for AI-mediated STEM instruction, and, specifically, on learner-LLM interaction are also discussed.
Study at a glance
- Question: How can multi-turn prompting be conceptualized and analyzed as an epistemic practice in science education?
- Setting and data: Not stated in the paper (conceptual paper analyzing prior literature, no empirical data collected).
- Method: Conceptual model paper synthesizing literature.
Why it matters
Prompt engineering treats prompts as inputs to optimize AI outputs, but learning requires understanding how tasks are framed, models are challenged, and knowledge is validated across multi-turn interactions.
Key findings
- Epistemic prompting shifts the focus from isolated prompt outputs to prompt trajectories that make problem framing, assumptions, and validation criteria open to inspection.
- Prompts function across a recursive loop of seeing, thinking, and acting by establishing, maintaining, specifying, challenging, repairing, transforming, reframing, or closing tasks.
- Effective student learning requires regulated delegation, where models provide calculations or alternatives while learners retain responsibility for problem framing, justification, and closure checks.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who age?
Study design
