Large Language Models Meet User Interfaces: The Case of Provisioning Feedback

TL;DR

This paper proposes a framework for ethically integrating Large Language Models into educational tools, exemplified by Feedback Copilot, to improve personalized student feedback while addressing usability and ethical challenges.

Contribution

It introduces a novel framework for ethical LLM integration in education and demonstrates its application through a new tool, Feedback Copilot, enhancing feedback personalization.

Findings

Effective personalized feedback provided by Feedback Copilot

Framework addresses ethical, privacy, and usability challenges

Demonstrates potential for scalable LLM-based educational tools

Abstract

Incorporating Generative AI (GenAI) and Large Language Models (LLMs) in education can enhance teaching efficiency and enrich student learning. Current LLM usage involves conversational user interfaces (CUIs) for tasks like generating materials or providing feedback. However, this presents challenges including the need for educator expertise in AI and CUIs, ethical concerns with high-stakes decisions, and privacy risks. CUIs also struggle with complex tasks. To address these, we propose transitioning from CUIs to user-friendly applications leveraging LLMs via API calls. We present a framework for ethically incorporating GenAI into educational tools and demonstrate its application in our tool, Feedback Copilot, which provides personalized feedback on student assignments. Our evaluation shows the effectiveness of this approach, with implications for GenAI researchers, educators, and technologists. This work charts a course for the future of GenAI in education.