2024 ASEE Annual Conference & Exposition

Learning never ends and there is no age limit to grow yourself. However, the educational landscape may face challenges in effectively catering to the inclusion and diverse learning needs of students, particularly those with special needs. These students are integral part of any educational environment and should have access to state-of-art methods for lecture delivery, online resources, and technology needs. Traditional assistive technologies and learning aids often lack the dynamic adaptability required for individualized education plans. Large Language Models (LLM) have been used in language translation, text summarization, and content generation applications [1]. With rapid growth in AI over the past years, AI-powered chatbots and virtual assistants have been developed [2] for conversational language understanding and generation. This work-in-progress project aims to bridge this gap by introducing an innovative study buddy we will be calling the ‘SAMCares’. The system leverages a Large Language Model (LLM) (in our case, llama-2 70B as the base model) and Retriever-Augmented Generation (RAG) to offer real-time, context-aware, and adaptive educational support. The context of the model will be kept limited to the knowledge base of Sam Houston State University (SHSU) courses. The LLM component enables a chat-like environment to interact with it to meet the unique learning requirements of each student. For this we will build a custom web-based GUI that can be accessed by the students with SHSU credentials. At the same time, RAG enhances real-time information retrieval and text generation, in turn providing more accurate and context-specific assistance. Students can upload their study materials in the web GUI and can start interacting with the materials to attain their learning goals. The system's efficacy will be evaluated through controlled trials and iterative feedback mechanisms. By interlinking Artificial Intelligence and assistive technology in an educational setting, this project aspires to advance personalized learning experiences for students with special needs, making meaningful strides in inclusive education.
Project Timeline: (September 1, 2023 – August 31, 2024)
Activity SEP OCT NOV DEC JAN FEB MAR APR MAY JUN JUL AUG Post Project
Development of the LLM Interface X X X X
Deploying in Spring 2024 for Data Collection X X X X X
Training & Fine Tuning X X X X
Bi-Weekly Meetings X X X X X X X X X X X X

[1] Devlin, J., M.-W. Chang, K. Lee, and K. Toutanova (2018). BERT: pre-training of deep bidirectional transformers for language understanding. arXiv article available at: https://arxiv.org/abs/1810.04805.
[2] McKee, F. and D. Noever (2022). Chatbots in a botnet world. arXiv article available at: https://arxiv.org/abs/2212.11126.