Exploring How Multiple Levels of GPT-Generated Programming Hints Support or Disappoint Novices
This addresses the problem of ineffective adaptive feedback in programming education for novices, though it is incremental in improving existing LLM-based hint systems.
The study investigated how multiple levels of GPT-generated programming hints affect novices, finding that high-level natural language hints alone were often unhelpful or misleading, while adding lower-level hints like code examples better supported students.
Recent studies have integrated large language models (LLMs) into diverse educational contexts, including providing adaptive programming hints, a type of feedback focuses on helping students move forward during problem-solving. However, most existing LLM-based hint systems are limited to one single hint type. To investigate whether and how different levels of hints can support students' problem-solving and learning, we conducted a think-aloud study with 12 novices using the LLM Hint Factory, a system providing four levels of hints from general natural language guidance to concrete code assistance, varying in format and granularity. We discovered that high-level natural language hints alone can be helpless or even misleading, especially when addressing next-step or syntax-related help requests. Adding lower-level hints, like code examples with in-line comments, can better support students. The findings open up future work on customizing help responses from content, format, and granularity levels to accurately identify and meet students' learning needs.