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.

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.