# Small Language Models for Curriculum-based Guidance

arXiv: https://arxiv.org/abs/2510.02347 · HTML: https://mlsanity.com/paper/2510.02347/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Large Language Models for Education: A Survey and Outlook](https://mlsanity.com/paper/2403.18105/) (2024)
- [Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild](https://mlsanity.com/paper/1906.02569/) (2019)
- [Large Language Models for Education: A Survey](https://mlsanity.com/paper/2405.13001/) (2024)
- [Learning from Teaching Assistants to Program with Subgoals: Exploring the Potential for AI Teaching Assistants](https://mlsanity.com/paper/2309.10419/) (2023)
- [Analyzing LLM Usage in an Advanced Computing Class in India](https://mlsanity.com/paper/2404.04603/) (2024)

## Abstract (arXiv)

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.