Large Language Models (LLM) -- powerful algorithms that can generate and transform text -- are set to disrupt language learning education and text-based assessments as they allow for automation of text that can meet certain outcomes of many traditional assessments such as essays. While there is no way to definitively identify text created by this…

Paragraph structure has been identified as consisting of three distinct parts, which are the topic sentence, supporting sentences, and a paragraph ending sentence. Although topic sentences have been widely researched, similar consideration for paragraph endings has been less forthcoming. This discrepancy may be problematic as research suggests…

Writing is a difficult task for most students. Only 27% of all students in America can write proficiently at or above grade level (U.S. Department of Education, Institute of Education Sciences, 2012). With the recent adoption of rigorous standards (i.e., Common Core State Standards, Next Generation Science Standards), secondary students are…

The use of writing models with nonnative English speakers has received a certain amount of criticism--especially from teachers whose students copy models in their entirety or follow them too closely. The misuse of models has brought some teachers to the point where they believe that the best kind of pedagogy is to abandon writing models…

Recent assessment research joining cognitive psychology and psychometric theory has introduced a new technology, item generation. In algorithmic item generation, items are systematically created based on specific combinations of features that underlie the processing required to correctly solve a problem. Reading comprehension items have been more…