Diagram-based Input for Large Language Models to Support Accessible STEM Learning

Sarah Elizabeth Wegwerth, Alexa Urrea, Julia E. Winter

Track: Innovations in AI for Education (Day 1)

Paper Length: short-paper (2 pages + references)

Keywords: accessibility, STEM education, chemistry, Large Language Models, alt text

TL;DR: The article descibes a system for connecting diagram-based learning tools to LLMs for accessible STEM education, and a usability study with adults who are blind.

Abstract: To meet the accessibility needs of students who are blind or have low vision (BLV), detailed textual descriptions of STEM diagrams within interactive learning tools are created in real-time and correspond to the configurations of the interactive software system. The descriptions are read by screen readers as alternative (alt) text to provide infor-mation for BLV students to compose mental representations of the diagram. These descriptions provide a unique bridge from the visual language of STEM diagrams to natural language of Large Language Models (LLMs). By interfacing with an LLM, these descriptions are used for personalized exploration by the BLV user and to guide all learners through a defined pedagogical pathway. Results from a usability study with four BLV adults are reported.

Submission Number: 24