Ethel: A Virtual Teaching Assistant

TL;DR

Ethel is a virtual teaching assistant leveraging generative AI, augmented with course-specific materials to improve accuracy and relevance in physics education tasks.

Contribution

The paper introduces Project Ethel, which enhances AI-based teaching assistants with course-specific prompts and reference materials for better educational support.

Findings

Improved accuracy in physics problem solving

Enhanced relevance of feedback and grading

Potential for scalable personalized education

Abstract

Generative AI has shown potential in solving physics problems and providing feedback on assessments. However, results are sometimes still inaccurate, at the wrong level, or using notations and definitions not appropriate for a particular course. A possible solution is augmenting the prompts with course-specific reference materials. Also, for feedback on homework solutions and grading exams, the problem text and the sample solution or grading rubric can be injected into the prompts. Project Ethel at ETH Zurich aims to construct a virtual teaching assistant using these practices.