Chinese students show varied AI prompting skills across academic tasks
Generative artificial intelligence prompting strategies among Chinese university students across academic tasks
Human-Computer InteractionArtificial Intelligence
Summary
Students use artificial intelligence tools to help with their schoolwork, but how well they interact with these tools depends on how they ask questions or give instructions. This study found that Chinese university students feel confident in their ability to create and adjust prompts for AI, especially when giving context or refining their initial requests. However, their strategies don't change much based on the type of task, and some common approaches like using fixed templates are less popular. The study also points out that choosing the right information to include is more important than making prompts short.
What this means in practice
- •For educational software developers: Design AI tutoring tools that adapt prompting guidance based on task type to improve student interaction with generative AI.
- •For instructional designers: Create training materials that help students focus on selecting and organizing relevant information rather than just making prompts concise.
Authors
Lei Fan, Fangxue Liu
Abstract
Generative artificial intelligence (GenAI) is increasingly embedded in university learning, yet effective human-GenAI interaction depends not only on access to these tools but also on students' ability to formulate, evaluate, and refine prompts for academic tasks. This study examined university students' perceived GenAI prompting capability and reported prompting strategies. Questionnaire data from 234 students were analyzed using descriptive statistics, measurement modelling, scenario comparisons, structural associations, and qualitative coding of optional comments. Students reported using GenAI across diverse academic activities and generally expressed confidence in their prompting capabilities, particularly in providing relevant context and refining prompts following initial outputs. However, prompting strategies showed limited sensitivity to task types: specifying output format was more strongly endorsed in a creative workshop preparation scenario than in a research-oriented assignment, whereas other matched strategies showed no adjusted differences. Students also commonly endorsed both concise instructions and providing all relevant information at the outset, suggesting that effective brevity may depend more on selecting and organizing task-relevant information than on prompt length alone. By contrast, fixed prompt templates received lower endorsement than other prompting strategies. In the adopted factor model, perceived cognition showed the clearest unique association with perceived prompting capability, while open-ended responses highlighted prompt-intent alignment as a common challenge.