Cracking the Code: Evaluating Zero-Shot Prompting Methods for Providing Programming Feedback
Niklas Ippisch ⋅ Anna-Carolina Haensch ⋅ Markus Herklotz ⋅ Jan Simson ⋅ Jacob Beck ⋅ Malte Schierholz
2025 Poster
in
Workshop: ICLR 2025 Workshop on Human-AI Coevolution
in
Workshop: ICLR 2025 Workshop on Human-AI Coevolution
Abstract
We introduce an evaluation framework to assess the feedback given by large language models (LLMs) under different prompt engineering techniques and conduct a case study, systematically varying prompts to examine their influence on feedback quality for common programming errors in R. Our findings suggest that prompts recommending a stepwise approach improve precision, whereas omitting explicit details on which data to analyze can bolster error identification.
Chat is not available.
Successful Page Load