缩小差距：监督微调开源LLM作为专有模型在教学工具中的可行替代方案
Narrowing the Gap: Supervised Fine-Tuning of Open-Source LLMs as a Viable Alternative to Proprietary Models for Pedagogical Tools
AI总结：
本研究通过监督微调开源小模型（Qwen3-4B、Llama-3.1-8B、Qwen3-32B）于4万条真实编译器错误解释数据，证明其教学效果可媲美专有大模型，为教育工具提供可行且经济的替代方案。
摘要：
前沿大型语言模型（LLM），如ChatGPT和Gemini，能够为初学者解读晦涩难懂的编译器错误，但其计算规模、成本以及过度辅助的倾向使其在广泛的教学应用中存在问题。本研究证明，通过监督微调（SFT）增强的小型专用语言模型，为教育工具提供了一种更可行的替代方案。我们利用一个新的包含40,000条C编译器错误解释的数据集，该数据集源自真实的入门编程（CS1/2）学生生成的编程错误，并用于微调三个开源模型：Qwen3-4B、Llama-3.1-8B和Qwen3-32B。我们进行了双重评估，将专家人工评审与使用经过验证的LLM-as-judge集成对8,000条响应的大规模自动分析相结合。我们的结果表明，SFT显著提升了较小模型的教学质量，使其性能达到与更大模型相当的水平。我们分析了模型规模与质量之间的权衡，证实了在高质量、领域特定的数据上微调紧凑高效的模型，是创建驱动教育工具的专用模型的有效策略。我们提供了一种可复现的方法论，以促进在教育环境中更广泛地获取生成式AI能力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
