Data Science in Education

Carnegie Learning is developing LiveHintAI, a system designed to deliver contextually relevant, on-demand support to students learning mathematics. In middle school algebra, clarifying connections between algebraic relationships and their graphical representations on Cartesian coordinates is critical. This talk presents our collaborative work to enable LiveHintAI to dynamically generate Desmos plots during tutor-student dialogues. We’ll share some challenges we encountered and the techniques we used to overcome them.

Sparx Science is an online homework system used weekly by 400,000+ students in England, part of the broader Sparx portfolio which serves 2,600+ schools and 2.2m+ students.

Traditionally, open-response questions—requiring students to answer with anything from a few words to full paragraphs—have required marking by teachers. As a result, online homework systems typically relied on constrained question types, such as multiple-choice.
However, Large language models (LLMs) have opened the door to reliably mark and provide meaningful feedback on open-response tasks, supporting effective retrieval practice and challenging students to think deeply.

In this talk, we'll share our approach to using LLMs to automatically mark prose in Sparx Science, including: fine-tuning, prompt engineering, and everything in between.