Large language models (LLMs) offer an opportunity to make large-scale changes to educational content that would otherwise be too costly to implement. The work here highlights how LLMs (in particular GPT-4) can be prompted to revise educational math content ready for large scale deployment in real-world learning environments. We tested the ability…

Large language models (LLMs) offer an opportunity to make large-scale changes to educational content that would otherwise be too costly to implement. The work here highlights how LLMs (in particular GPT-4) can be prompted to revise educational math content ready for large scale deployment in real-world learning environments. We tested the ability…

The Raygor Readability Estimate, described in this article, is much like the widely used Fry Readability Graph, except that it determines vocabulary difficulty by counting words of six or more letters, rather than by counting syllables. An evaluation found that Raygor was faster and easier to use and more objective than the Fry method. (RM)

When readability formulas are used to review workbooks and textbooks their value is limited because application techniques have failed to take into consideration the exercises and examples in these books. The O'Hear and Ramsey (OR) Corrective technique has been developed to alleviate this problem. It allows readability data to be used accurately…