Solopova, Veronika, et al. PapagAI:Automated Feedback for Reflective Essays. arXiv, 10 July 2023. arXiv.org, https://doi.org/10.48550/arXiv.2307.07523.
Written reflective practice is a regular exercise pre-service teachers perform during their higher education. Usually, their lecturers are expected to provide individual feedback, which can be a challenging task to perform on a regular basis. In this paper, we present the first open-source automated feedback tool based on didactic theory and implemented as a hybrid AI system. We describe the components and discuss the advantages and disadvantages of our system compared to the state-of-art generative large language models. The main objective of our work is to enable better learning outcomes for students and to complement the teaching activities of lecturers.
I was initially excited when I read the title and abstract of the paper but it turns out that it’s ‘only’ an evaluation of the hybrid AI model, with some comparison to large language models. This paper doesn’t say anything about the quality of the automated feedback being generated but if the objective of the work is to “enable better learning outcomes”, you’d expect to see an evaluation of feedback at some point. Anyway, it points us in the direction that this is going.