Fine-Tuning Models for Automated Code Review Feedback

TL;DR

This study explores how parameter-efficient fine-tuning of open LLMs, specifically Code Llama, can improve automated code review feedback, making it comparable to proprietary models like ChatGPT.

Contribution

It demonstrates that PEFT significantly enhances feedback quality over prompt engineering, enabling effective, freely deployable educational tools.

Findings

PEFT improves feedback quality on buggy Java code

PEFT outperforms prompt engineering in feedback generation

Students find PEFT-generated feedback as effective as ChatGPT

Abstract

Large Language Models have introduced new possibilities for programming education through personalized support, content creation, and automated feedback. While recent studies have demonstrated the potential for feedback generation, many techniques rely on proprietary models, raising concerns about cost, computational demands, and the ethical implications of sharing student code. Open LLMs provide an alternative approach, but they do not currently have the capabilities of proprietary models. To address this problem, we investigate whether parameter-efficient fine-tuning (PEFT) and prompt engineering, both of which distil knowledge from a dataset derived from a large, more capable model, can be used to adapt and enhance the quality of feedback generated by the open LLM Code Llama. Feedback quality on buggy Java code was assessed using a combination of student evaluation, manual annotation and the automated metrics BLEU, ROUGE, and BERTScore. Our findings indicate that PEFT leads to notable improvements in feedback quality and significantly outperforms prompt engineering, providing an avenue for developing freely deployable feedback tools that can be effectively used to guide student learning. Student evaluation indicates that learners value the PEFT model's feedback and see it as being equally effective as the proprietary ChatGPT model. Participants suggested that incorporating additional explanation for technical terms in the PEFT model's feedback could be more beneficial. This study demonstrates that fine-tuned models can effectively support critical thinking and guide the design of scalable pedagogical systems.