The Future of Education

Generative AI (GenAI) enhances personalized teaching materials and reduces teachers' workload by generating formative and summative feedback to improve learner performance [1,2]. Prompt engineering, a skill that utilizes language and prior knowledge to construct prompts directing generative AI towards desired outcomes, encompasses basic knowledge of relevant language syntax and the strategic use of prompt modifiers [3].

Given that lesson planning is a time-intensive and labor-intensive task, GenAI tools can provide significant assistance. Some studies have explored the use of GenAI in designing lesson plans, demonstrating advantages in areas such as setting instructional objectives and identifying teaching priorities [1,4]. However, the role of GenAI in assisting users with lesson plan assessment tasks remains understudied.

In this study, we explored prompt strategies in lesson plan assessment tasks using prompts generated during human-GenAI interactions. With this goal, a GenAI tool was employed in lesson plan assessment activities by pre-service secondary school physics course teachers. We adopted a qualitative research approach. A prompt dataset from 45 pre-service teachers was collected and served as our data source.

Through interpretive analysis of the qualitative data, we found that different prompt approaches were employed when learners were stuck or dissatisfied with the generated outputs. Our findings both align with and differ from previous studies [5]. We summarized prompt strategies for lesson plan assessment activities, contributing to the effective use of GenAI in lesson planning tasks by providing practical suggestions for real-world educational contexts.

Keywords: Prompt Engineering, Lesson Plan Assessment, Qualitative Research, Pre-service Teachers

REFERENCES

[1] Hu B., Zheng L., Zhu J., Ding L., Wang Y., Gu X., “Teaching Plan Generation and Evaluation With GPT-4: Unleashing the Potential of LLM in Instructional Design”, IEEE Transactions on Learning Technologies, 2024.

[2] Meyer J., Jansen T., Schiller R., Liebenow L. W., Steinbach M., Horbach A., Fleckenstein J., “Using LLMs to bring evidence-based feedback into the classroom: AI-generated feedback increases secondary students’ text revision, motivation, and positive emotions”, Computers and Education: Artificial Intelligence, 2024, 6, 100199.

[3] Oppenlaender J., Linder R., Silvennoinen J., “Prompting AI art: An investigation into the creative skill of prompt engineering”, International Journal of Human–Computer Interaction, 2024, 1-23.

[4] Hasan Z. O., Muslu N., “Designing a course for pre-service science teachers using ChatGPT: what ChatGPT brings to the table”, Interactive Learning Environments, 2024.

[5] Zamfirescu-Pereira J. D., Wong R. Y., Hartmann B., Yang Q., “Why Johnny can’t prompt: how non-AI experts try (and fail) to design LLM prompts”, Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, 2023, 1-21.