面向基于课程的引导的小型语言模型
Small Language Models for Curriculum-based Guidance
AI总结：
本研究将RAG流水线应用于开源小型语言模型构建AI教学助手，测试发现经恰当提示与定向检索的70-170亿参数SLM，教学回复准确性可匹配GPT-4o，且更低碳低成本、可离线运行，适用于教育机构规模化个性化学习。
摘要：
生成式人工智能与大语言模型（LLMs）在教育领域的应用仍处于新兴阶段。本研究探索了AI教学助手的开发与评估，这类助手通过将检索增强生成（RAG，Retrieval-Augmented Generation）流水线应用于精选的开源小型语言模型（SLMs），提供基于课程的引导。我们以GPT-4o为基准，对8款SLM（包括LLaMA 3.1、IBM Granite 3.3和Gemma 3，参数量为70-170亿）开展了基准测试。研究结果表明，借助恰当的提示词设计与定向检索，SLMs在生成准确、符合教学要求的回复方面可与LLMs媲美。值得注意的是，SLMs因计算与能耗需求更低，具备显著的可持续性优势，可在消费级硬件上实时运行，无需依赖云基础设施。这使其不仅具备成本效益且能保护隐私，还兼具环境责任感，有望成为教育机构以可持续、高能效方式规模化推广个性化学习的可行AI教学助手。
英文摘要：
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.
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。
