Generating Planning Feedback for Open-Ended Programming Exercises with LLMs

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Demirtaş, Mehmet Arif, Zheng, Claire, Fowler, Max, Cunningham, Kathryn
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915238039781376
author Demirtaş, Mehmet Arif
Zheng, Claire
Fowler, Max
Cunningham, Kathryn
author_facet Demirtaş, Mehmet Arif
Zheng, Claire
Fowler, Max
Cunningham, Kathryn
contents To complete an open-ended programming exercise, students need to both plan a high-level solution and implement it using the appropriate syntax. However, these problems are often autograded on the correctness of the final submission through test cases, and students cannot get feedback on their planning process. Large language models (LLM) may be able to generate this feedback by detecting the overall code structure even for submissions with syntax errors. To this end, we propose an approach that detects which high-level goals and patterns (i.e. programming plans) exist in a student program with LLMs. We show that both the full GPT-4o model and a small variant (GPT-4o-mini) can detect these plans with remarkable accuracy, outperforming baselines inspired by conventional approaches to code analysis. We further show that the smaller, cost-effective variant (GPT-4o-mini) achieves results on par with state-of-the-art (GPT-4o) after fine-tuning, creating promising implications for smaller models for real-time grading. These smaller models can be incorporated into autograders for open-ended code-writing exercises to provide feedback for students' implicit planning skills, even when their program is syntactically incorrect. Furthermore, LLMs may be useful in providing feedback for problems in other domains where students start with a set of high-level solution steps and iteratively compute the output, such as math and physics problems.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08958
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generating Planning Feedback for Open-Ended Programming Exercises with LLMs
Demirtaş, Mehmet Arif
Zheng, Claire
Fowler, Max
Cunningham, Kathryn
Computation and Language
Artificial Intelligence
To complete an open-ended programming exercise, students need to both plan a high-level solution and implement it using the appropriate syntax. However, these problems are often autograded on the correctness of the final submission through test cases, and students cannot get feedback on their planning process. Large language models (LLM) may be able to generate this feedback by detecting the overall code structure even for submissions with syntax errors. To this end, we propose an approach that detects which high-level goals and patterns (i.e. programming plans) exist in a student program with LLMs. We show that both the full GPT-4o model and a small variant (GPT-4o-mini) can detect these plans with remarkable accuracy, outperforming baselines inspired by conventional approaches to code analysis. We further show that the smaller, cost-effective variant (GPT-4o-mini) achieves results on par with state-of-the-art (GPT-4o) after fine-tuning, creating promising implications for smaller models for real-time grading. These smaller models can be incorporated into autograders for open-ended code-writing exercises to provide feedback for students' implicit planning skills, even when their program is syntactically incorrect. Furthermore, LLMs may be useful in providing feedback for problems in other domains where students start with a set of high-level solution steps and iteratively compute the output, such as math and physics problems.
title Generating Planning Feedback for Open-Ended Programming Exercises with LLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2504.08958