Improving the Validity of Automatically Generated Feedback via Reinforcement Learning

arXiv:2403.01304v1 Announce Type: new
Abstract: Automatically generating feedback via large language models (LLMs) in intelligent tutoring systems and online learning platforms has the potential to improve the learning outcomes of many students. However, both feedback generation and evaluation are challenging: feedback content has to be valid especially in subjects like math, which requires models to understand the problem, the solution, and where the student's error lies. Feedback also has to be pedagogically valid to reflect effective tutoring strategies, such as …

abstract arxiv cs.cl evaluation feedback generated intelligent language language models large language large language models llms online learning platforms reinforcement reinforcement learning students systems tutoring type via