We conducted a post hoc analysis of 771 students’ argumentative writing plans and essays in the Criterion ® database, a digital writing tool, to explore the relations among plan features, essay quality, and writing traits. Students in the study were in Grades 5 to 10 from 68 schools. We found that older students produced writing plans that received higher scores and demonstrated greater genre-specific knowledge than younger students, but regardless of their grade, most students did not consider alternative perspectives or rebut counterarguments in their writing plans. We also found that students’ choice of plan templates was associated with the scores of their plans. Further, factor analysis showed that six of the seven plan feature scores hung together in a single factor (Factor 1) and correlated with multiple trait scores (Factor 2), accounting for most of the shared variance connecting plan scores with writing traits. The “both sides” plan feature loaded on a different factor by its own, suggesting that considering different perspectives is a challenging skill that students may need extra support to develop.

In this study, we examine the feasibility of augmenting student-written essays with those generated by large language models (LLMs) for scoring essays. We found that with correct instructions, generative AI systems such as GPT-4 and GPT-4o can generate essays similar to those written by students in terms of surface-level linguistic features, although material differences may still exist. Systematic analyses revealed that scoring models trained with synthetic data perform comparably to models trained using student essays, but the performance varies across prompts and the sizes of the model training sample. The augmented models could alleviate large discrepancies between human and AI scores on the subgroup level that may be introduced by a lack of training samples for a particular subgroup or due to inherent biases in LLMs. We also explored an established method – DecompX – on token importance to identify and explain AI predictions. Future research directions and limitations of this study are also discussed.

The reflective essay introduces the culminating project from a specific iteration of Perspectives on the Humanities, the second universally required composition course at NYU Shanghai. For this project, students investigate a self-selected term of sociocultural significance that defies smooth migration across linguistic boundaries, especially between English and Chinese. Students can convey their research and insights through one of three genres: a “traditional” argumentative essay, an extended note, or a historical narrative. Inspired in part by Raymond Williams, this assignment aims to enhance students' rhetorical, linguistic, and cultural awareness by navigating the complexities of language and genre in a globalized context.