基于上下文提示的人工智能驱动物理作业

中文摘要 AI 辅助

生成式人工智能（Gen AI）日益影响着学生获取信息和参与物理内容的方式，然而许多教学方法仍假设课堂处于前人工智能时代。在本文中，我们描述了一个通过使用上下文提示将生成式人工智能整合到物理教学中的实用框架：上下文提示是由教师设计的提示，用于定义人工智能交互的角色、任务和边界。我们重点介绍了在一个约70名学生的异步入门物理课程中实施的基于人工智能支持的探索性作业。在这些活动中，学生将人工智能用作引导式导师，探索选定主题、提出后续问题、请求解释和类比，并将物理概念与个人兴趣和日常经验联系起来。我们认为，这种结构有助于学生超越寻求答案，转向更具对话性和个人意义的内容参与。我们还讨论了反思作为同一框架的自然延伸，同时将其与本文所述的已实施探索活动区分开来。最后，我们强调了使用中出现的实际考虑因素，包括人工智能平台访问不均、评分工作量、需要教授学生如何以对话方式使用人工智能，以及人工智能素养在物理教育中日益增长的重要性。

英文摘要

Generative artificial intelligence (Gen AI) is increasingly shaping how students access information and engage with physics content, yet many instructional approaches still assume a pre-AI classroom. In this paper, we describe a practical framework for integrating Gen AI into physics instruction through the use of context prompts: instructor-designed prompts that define the role, task, and boundaries of the AI interaction. We focus on AI-supported exploration assignments implemented in an asynchronous introductory physics course enrolling approximately 70 students. In these activities, students used AI as a guided tutor to explore selected topics, ask follow-up questions, request explanations and analogies, and connect physics concepts to their personal interests and everyday experiences. We argue that this structure can help move students beyond answer-seeking and toward more dialogic and personally meaningful engagement with course content. We also discuss reflection as a natural extension of the same framework, while distinguishing it from the implemented exploration activities described here. Finally, we highlight practical considerations that emerged in use, including uneven access to AI platforms, grading workload, the need to teach students how to engage AI conversationally, and the growing importance of AI literacy in physics education.

发表机构

• California State University, Dominguez Hills（加州州立大学多明格斯山分校）
• Ludwigsburg University of Education（路德维希堡教育学院）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

6 pages, 1 figure