2023 · 57 citations · 31 references
ComputingComputer ScienceNatural Language ProcessingProblem-based LearningSyntaxCode GenerationLanguage ModelingNatural Language GenerationProblem-solving StrategiesText GenerationDesign-based Problem SolvingLarge Language ModelsModel Performance EvaluationPrompt-based Generation
The recent emergence of code generation tools powered by large language models has attracted wide attention. Models such as OpenAI Codex can take natural language problem descriptions as input and generate highly accurate source code solutions, with potentially significant implications for computing education. Given the many complexities that students face when learning to write code, they may quickly become reliant on such tools without properly understanding the underlying concepts. One popular approach for scaffolding the code writing process is to use Parsons problems, which present solution lines of code in a scrambled order. These remove the complexities of low-level syntax, and allow students to focus on algorithmic and design-level problem solving. It is unclear how well code generation models can be applied to solve Parsons problems, given the mechanics of these models and prior evidence that they underperform when problems include specific restrictions. In this paper, we explore the performance of the Codex model for solving Parsons problems over various prompt variations. Using a corpus of Parsons problems we sourced from the computing education literature, we find that Codex successfully reorders the problem blocks about half of the time, a much lower rate of success when compared to prior work on more free-form programming tasks. Regarding prompts, we find that small variations in prompting have a noticeable effect on model performance, although the effect is not as pronounced as between different problems.
31
Programming Is Hard - Or at Least It Used to Be
Brett A. Becker, Paul Denny, James Finnie-Ansley et al. · 2023 · 330 citations · Full text
Using Large Language Models to Enhance Programming Error Messages
Juho Leinonen, Arto Hellas, Sami Sarsa et al. · 2023 · 209 citations · Full text
Generating Diverse Code Explanations using the GPT-3 Large Language Model
Stephen MacNeil, Andrew Tran, Dan Mogil et al. · 2022 · 200 citations
Computing, Computer Science, Intelligent Tutoring Systems +16