UIUC AI Teaching Assistant
A team at UIUC has developed an open-source AI teaching assistant for electrical engineering students, utilizing 11 parallel models for tasks like retrieval and moderation. The project emphasizes iterative evaluation using human-expert feedback and GPT-3 to refine its responses.
Why it matters
This project demonstrates a practical, low-latency application of LLMs in education and provides a transparent framework for others to build similar academic tools.
We're live on HuggingFace: 👉 https://huggingface.co/spaces/kastan/ai-teaching-assistant 👈 System diagram Our system runs 11 separate models in parallel for text/image retrieval, generation, moderation and ranking and still achieves a median 2-second response time.
We use data from textbooks, lecture videos, and student QA forums (ordered, subjuctively, by importance). None of this data is currently available publically because this project was not granted those rights by the authors.
My favorite contribution is the novel approach of semantic search retrieval during RLHF, using a dataset I iteratively produced by hiring a team of five Electrical Engineering students. That data is freely available on Huggingface here: https://huggingface.co/datasets/kastan/rlhf-qa-comparisons . We specifically cover the material necessary in the UIUC course ECE 120, intro to Electrical Engineering.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in