A large language model-assisted education tool to provide feedback on open-ended responses
This tool addresses the problem of instructor workload and feedback quality in education, offering a practical solution for enhancing learning outcomes, though it is incremental as it applies existing LLM technology to a specific educational context.
The researchers tackled the time-consuming task of providing feedback on open-ended student responses by developing a tool that uses large language models guided by instructor criteria to automate personalized feedback, enabling rapid student assessment and improvement.
Open-ended questions are a favored tool among instructors for assessing student understanding and encouraging critical exploration of course material. Providing feedback for such responses is a time-consuming task that can lead to overwhelmed instructors and decreased feedback quality. Many instructors resort to simpler question formats, like multiple-choice questions, which provide immediate feedback but at the expense of personalized and insightful comments. Here, we present a tool that uses large language models (LLMs), guided by instructor-defined criteria, to automate responses to open-ended questions. Our tool delivers rapid personalized feedback, enabling students to quickly test their knowledge and identify areas for improvement. We provide open-source reference implementations both as a web application and as a Jupyter Notebook widget that can be used with instructional coding or math notebooks. With instructor guidance, LLMs hold promise to enhance student learning outcomes and elevate instructional methodologies.