小模型加检索增强，实现低成本高效教学辅导
Small Language Models for Curriculum-based Guidance
- 用小模型结合检索增强生成，精准匹配课程内容
- 8个7-17B参数小模型在提示工程下媲美GPT-4o
- 可本地运行、省电节能，适合教育机构规模化部署
生成式AI与大语言模型在教育领域的应用仍处于起步阶段。本研究探索了基于检索增强生成（RAG）管道的开源小语言模型（SLMs）在课程引导型教学助手中的开发与评估。我们对八种SLMs（包括LLaMA 3.1、IBM Granite 3.3、Gemma 3，参数量7-17B）进行了测试，对比GPT-4o表现。结果表明，通过合理提示和定向检索，小模型能提供与大模型相当的准确且符合教学逻辑的回答。更重要的是，小模型计算与能耗更低，可在消费级硬件上实时运行，无需依赖云服务，兼具成本低、隐私保护与环保优势，为追求可持续、高效个性化学习的教育机构提供了可行的AI助教方案。
原文摘要 · Abstract (English)
The adoption of generative AI and large language models (LLMs) in education is still emerging. In this study, we explore the development and evaluation of AI teaching assistants that provide curriculum-based guidance using a retrieval-augmented generation (RAG) pipeline applied to selected open-source small language models (SLMs). We benchmarked eight SLMs, including LLaMA 3.1, IBM Granite 3.3, and Gemma 3 (7-17B parameters), against GPT-4o. Our findings show that with proper prompting and targeted retrieval, SLMs can match LLMs in delivering accurate, pedagogically aligned responses. Importantly, SLMs offer significant sustainability benefits due to their lower computational and energy requirements, enabling real-time use on consumer-grade hardware without depending on cloud infrastructure. This makes them not only cost-effective and privacy-preserving but also environmentally responsible, positioning them as viable AI teaching assistants for educational institutions aiming to scale personalized learning in a sustainable and energy-efficient manner.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。