Though it did review 118 studies using Large Language Models (LLM) to automate educational tasks, it's probably somewhat early for a literature review on this subject, and this would explain the paucity of the "comprehensive list of different educational tasks that could potentially benefit from LLMs-based innovations" in this paper (23 page PDF). I don't mean to keep referring back to my ethics course, but none of these papers match my own list of applications or ethical issues (I'd publish both, but they're too long for journals to accept). Still, it's good to have something like this in the literature, and I agree with the observations that "LLMs-based innovations are subject to data privacy issues but were rarely mentioned or investigated in the literature" and that "the reporting standards of empirical research that aims to develop educational technologies using large language models need to be improved."
Today: 4 Total: 4 [Share]
] [