Generative AI, particularly Language Models (LMs), has the potential to transform real-world domains with societal impact, particularly where access to experts is limited. For example, in education, training novice educators with expert guidance is important for effectiveness but expensive, creating significant barriers to improving education…

PIRLS is an international assessment of reading comprehension at the fourth grade that has been conducted every five years since 2001. In 2011, nationally representative samples of students in 49 countries participated in PIRLS and prePIRLS. Forty-five countries assessed fourth grade students, and some countries participated in one or more of the…