Small Language Models for Curriculum-based Guidance
This addresses the problem of scalable and sustainable AI teaching assistants for educational institutions, though it is incremental as it applies existing methods to new data.
The study tackled the challenge of providing curriculum-based guidance in education by developing AI teaching assistants using small language models (SLMs) with a retrieval-augmented generation pipeline, finding that SLMs can match GPT-4o in accuracy and offer sustainability benefits like lower computational requirements.
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.