🤖 AI Summary
This study addresses the challenge that students with limited metacognitive skills struggle to formulate targeted questions for AI systems, often resulting in ineffective help-seeking or over-reliance. We propose HelpCoach, a plugin that embeds metacognitive training within specific problem-solving tasks. By leveraging real-time assessment algorithms and adaptive revision templates, the system delivers immediate feedback to guide students in dynamically optimizing their questioning strategies during interaction. This approach overcomes the limitations of traditional decontextualized pre-training by enabling situated behavioral correction. Experimental results demonstrate that the plugin significantly enhances both the specificity of student queries and knowledge retention, outperforming baseline methods that rely solely on prior instruction.
📝 Abstract
Students increasingly turn to AI for help with problem-solving, yet too much AI support can undermine learning itself. To benefit from AI, students need to specify the necessary knowledge and scaffold type in their questions. However, they struggle to formulate such targeted questions because they lack metacognitive skills to recognize and select effective help options. We developed HelpCoach, an add-on for chat interfaces that helps students formulate knowledge- and scaffold-specific questions and receive targeted help during problem solving. HelpCoach continuously assesses students' help-seeking performance and prompts students to improve through an adaptive revision template. Whereas prior work has largely taught help-seeking skills apart from learning tasks, HelpCoach's in situ scaffold enables concrete practice on metacognitive skills and immediate revisions to help-seeking behavior. In a study with 40 college students learning web programming, HelpCoach led to more specific questions during chatbot interactions and greater knowledge retention than pre-task help-seeking training alone.