Pre-service Language Teachers’ Task-specific Large Language Model Prompting Practices
Problem
How pre-service language teachers can use large language models to improve lesson plans, and what knowledge and skills their task-specific prompting requires.
Why it matters
Effective LLM prompting can ease teachers' lesson-planning workload and inform teacher training.
What the AI did
Teachers interacted with LLMs to revise lesson plans; the study analyzed their assignments, interaction logs, and reflections to characterize their prompting practices.
Results
Identified a three-stage decision-making process: task identification, iterative prompting, and a third stage truncated in the abstract.
Impact
Documents a three-stage prompting process among 25 pre-service teachers at a Hong Kong university.
Record
| Venue | RELC Journal |
|---|---|
| Published | 2025 |
| Work type | article |
| Authors | Benjamin Luke Moorhouse, Tsz Ying Ho, Chenze Wu, Yuwei Wan |
| Citations | 25 (OpenAlex, at import time) |
| References | 19 |
| Model or method | LLMs; ChatGPT mentioned in abstract |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1177/00336882251313701 |
| Open access | closed |
| Keywords | LLM prompting, pre-service teachers, lesson planning, ChatGPT, teacher education |
Importance rating
incremental / niche
LLM-assisted lesson planning for pre-service teachers; small qualitative study relevant to teacher training; no broad scale stated.