Document Type
Poster
Publication Date
Fall 2024
Abstract
When students with disabilities enter the college arena they lose many of the resources that supported them throughout high school, and suddenly are responsible for advocating for their needs and rights themselves. For some, this is an easy transition, but for most the sudden shift in setting, expectations, and responsibilities leaves them unprepared to transition smoothly into college life. A chatbot with sufficient institutional data and information about disabilities and accommodations could help college students with disabilities by providing immediate and personalized guidance throughout their college experience. The proposed accessibility support system implements a hybrid architecture combining a Retrieval-Augmented Generation (RAG) pipeline with an agent-based framework powered by LangChain. The RAG component enables context-aware responses by retrieving relevant institutional knowledge from a vector database, while the agent architecture facilitates autonomous decision-making and tool utilization through a chain-of-thought reasoning process. The system incorporates carefully engineered prompts and few-shot learning examples to guide interaction patterns, with particular emphasis on emotional intelligence through affect-aware response generation. This multi-faceted approach enables the agent to provide both informationally accurate and emotionally resonant support for students with disabilities in higher education settings.
Recommended Citation
Sussman, Hannah and Chun, Jon, "AI Virtual Assistant for Student Disability Services: Implementing RAG-Enhanced Chatbots in Higher Education Support" (2024). IPHS 391: Interdisciplinary AI Frontiers. Paper 6.
https://digital.kenyon.edu/dh_iphs_391/6
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.