Navigating Pitfalls: Evaluating LLMs in Machine Learning Programming Education

TL;DR

This study evaluates the effectiveness of various LLMs in identifying common errors in machine learning code to support education, revealing their strengths, limitations, and potential for guiding learners.

Contribution

It provides a comparative analysis of closed and open LLMs in detecting ML coding pitfalls, highlighting current limitations and opportunities for deploying smaller models in education.

Findings

Basic pitfalls are easily identified by all models.

Many complex pitfalls, especially in early ML pipeline stages, are not well detected.

LLMs can provide useful feedback and guidance when they identify pitfalls.

Abstract

The rapid advancement of Large Language Models (LLMs) has opened new avenues in education. This study examines the use of LLMs in supporting learning in machine learning education; in particular, it focuses on the ability of LLMs to identify common errors of practice (pitfalls) in machine learning code, and their ability to provide feedback that can guide learning. Using a portfolio of code samples, we consider four different LLMs: one closed model and three open models. Whilst the most basic pitfalls are readily identified by all models, many common pitfalls are not. They particularly struggle to identify pitfalls in the early stages of the ML pipeline, especially those which can lead to information leaks, a major source of failure within applied ML projects. They also exhibit limited success at identifying pitfalls around model selection, which is a concept that students often struggle with when first transitioning from theory to practice. This questions the use of current LLMs to support machine learning education, and also raises important questions about their use by novice practitioners. Nevertheless, when LLMs successfully identify pitfalls in code, they do provide feedback that includes advice on how to proceed, emphasising their potential role in guiding learners. We also compare the capability of closed and open LLM models, and find that the gap is relatively small given the large difference in model sizes. This presents an opportunity to deploy, and potentially customise, smaller more efficient LLM models within education, avoiding risks around cost and data sharing associated with commercial models.