# Narrowing the Gap: Supervised Fine-Tuning of Open-Source LLMs as a Viable Alternative to Proprietary Models for Pedagogical Tools

arXiv: https://arxiv.org/abs/2507.05305 · HTML: https://mlsanity.com/paper/2507.05305/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 7 Jul 2025.

## Builds on (most cited first, 16 of 16)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Using Large Language Models to Enhance Programming Error Messages](https://mlsanity.com/paper/2210.11630/) (2022)
- [Large Language Models (GPT) for automating feedback on programming assignments](https://mlsanity.com/paper/2307.00150/) (2023)
- [Exploring the Potential of Large Language Models to Generate Formative Programming Feedback](https://mlsanity.com/paper/2309.00029/) (2023)
- [AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs](https://mlsanity.com/paper/2311.02775/) (2023)
- [Improving the Validity of Automatically Generated Feedback via Reinforcement Learning](https://mlsanity.com/paper/2403.01304/) (2024)
- [Open Source Language Models Can Provide Feedback: Evaluating LLMs' Ability to Help Students Using GPT-4-As-A-Judge](https://mlsanity.com/paper/2405.05253/) (2024)
- [Beyond the Hype: A Comprehensive Review of Current Trends in Generative AI Research, Teaching Practices, and Tools](https://mlsanity.com/paper/2412.14732/) (2024)
- [Evaluating Contextually Personalized Programming Exercises Created with Generative AI](https://mlsanity.com/paper/2407.11994/) (2024)
- [Evaluating Language Models for Generating and Judging Programming Feedback](https://mlsanity.com/paper/2407.04873/) (2024)
- [Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation](https://mlsanity.com/paper/2406.05053/) (2024)
- [Supervised Fine-Tuning LLMs to Behave as Pedagogical Agents in Programming Education](https://mlsanity.com/paper/2502.20527/) (2025)
- [Not the Silver Bullet: LLM-enhanced Programming Error Messages are Ineffective in Practice](https://mlsanity.com/paper/2409.18661/) (2024)
- [Debugging Without Error Messages: How LLM Prompting Strategy Affects Programming Error Explanation Effectiveness](https://mlsanity.com/paper/2501.05706/) (2025)

## Built on by (most cited first, 1 of 1)

- [Performance Trade-offs of Optimizing Small Language Models for E-Commerce](https://mlsanity.com/paper/2510.21970/) (2025)

## Abstract (arXiv)

Frontier Large language models (LLMs) like ChatGPT and Gemini can decipher cryptic compiler errors for novice programmers, but their computational scale, cost, and tendency to over-assist make them problematic for widespread pedagogical adoption. This work demonstrates that smaller, specialised language models, enhanced via Supervised Fine-Tuning (SFT), present a more viable alternative for educational tools. We utilise a new dataset of 40,000 C compiler error explanations, derived from real introductory programming (CS1/2) student-generated programming errors, which we used to fine-tune three open-source models: Qwen3-4B, Llama-3.1-8B, and Qwen3-32B. We performed a dual evaluation, combining expert human reviews with a large-scale automated analysis of 8,000 responses using a validated LLM-as-judge ensemble. Our results show that SFT significantly boosts the pedagogical quality of smaller models, achieving performance comparable to much larger models. We analyse the trade-offs between model size and quality, confirming that fine-tuning compact, efficient models on high-quality, domain-specific data is a potent strategy for creating specialised models to drive educational tools. We provide a replicable methodology to foster broader access to generative AI capabilities in educational contexts.