Prompt-Based Cost-Effective Evaluation and Operation of ChatGPT as a Computer Programming Teaching Assistant

TL;DR

This paper evaluates GPT models for providing programming feedback, proposes prompt techniques to automate evaluation, and discusses strategies for deploying LLMs as teaching assistants in programming education.

Contribution

It introduces a prompt-based method to assess LLM feedback quality and outlines a practical strategy for using LLMs as programming teaching assistants.

Findings

GPT-4T outperforms GPT-3.5T but still generates some incorrect feedback.

Proposed prompts enable automated evaluation and diagnostic analysis.

A strategy for deploying LLMs as educational tools is outlined.

Abstract

The dream of achieving a student-teacher ratio of 1:1 is closer than ever thanks to the emergence of large language models (LLMs). One potential application of these models in the educational field would be to provide feedback to students in university introductory programming courses, so that a student struggling to solve a basic implementation problem could seek help from an LLM available 24/7. This article focuses on studying three aspects related to such an application. First, the performance of two well-known models, GPT-3.5T and GPT-4T, in providing feedback to students is evaluated. The empirical results showed that GPT-4T performs much better than GPT-3.5T, however, it is not yet ready for use in a real-world scenario. This is due to the possibility of generating incorrect information that potential users may not always be able to detect. Second, the article proposes a carefully designed prompt using in-context learning techniques that allows automating important parts of the evaluation process, as well as providing a lower bound for the fraction of feedbacks containing incorrect information, saving time and effort. This was possible because the resulting feedback has a programmatically analyzable structure that incorporates diagnostic information about the LLM's performance in solving the requested task. Third, the article also suggests a possible strategy for implementing a practical learning tool based on LLMs, which is rooted on the proposed prompting techniques. This strategy opens up a whole range of interesting possibilities from a pedagogical perspective.