Rhetor: Providing LLM-Based Feedback for Students’ Argumentative Essays

This study introduces the design and evaluation of an essay tutoring application based on a large language model (LLM). We created an LLM-based prototype tool to provide personalized feedback, with the goal of improving students’ argumentative writing and critical thinking skills, grounded in learning sciences principles (i.e., scaffolding and worked examples). We conducted user testing and interviews with participants from a large U.S.-based educational testing company and writing education experts. Overall, the participants found the system easy to use and believed it could augment human tutors’ abilities. We presented nine design principles for LLM-based essay-writing tutors based on the results.