Revising LLM Text to (Re)Discover Rhetoric

This assignment, by Clancy Ratliff, is from the book Teaching and Generative AI.

The Abstract from the article explains:

In this essay, I share an assignment that asks students to engage in rhetorical revision of LLM text using a changelog table as a tool to document the revision. To demonstrate to the students what I was asking them to do, I did the assignment myself, and my example is included in this chapter as well. I argue that the style of generated text from LLMs calls for increased resistance to the norms and conventions of school writing and an embrace of writing that’s more rhetorical: a bit more personal, risky, rule-breaking, creative, and experimental, intentionally centering purpose and audience. I gave this assignment in a graduate course, but it would work equally well in an undergraduate course.

Key Features of This Assignment

Rhetorical Revision

The assignment encourages students to revise AI-generated text to make it more rhetorical, focusing on purpose, audience, and persuasion, thus enhancing their understanding and application of rhetorical principles.

Changelog Documentation

Students document their revisions in a changelog, explaining the rationale behind each change. This process makes the revision process transparent and helps students reflect on their editing decisions.

Reflective Practice

Students write a reflection on their experience revising the AI-generated text, promoting critical thinking about their writing process and the role of AI in writing.

Find the full version of this resource in the book Teaching and Generative AI.