This assignment, by João Gonçalves and Sarah Young, is from the TextGenEd: Continuing Experiments collection on the WAC Clearinghouse website.
The summary from the site explains:
This assignment asks undergraduate students to train their own language model based on a set of text documents that they select. It provides them with code to do so on the free Google Colab platform, as well as detailed instructions. It allows them to understand the mechanisms behind language models and the requirements to train them, which in turn translates to higher levels of AI literacy. This approach is especially useful to foster a more critical use of generative AI by students, highlighting the links between training data and model outputs.
Key Features of This Assignment
- Prompt Engineering
- The article explains how to craft precise prompts that guide AI responses, thereby enhancing clarity and creative potential in written assignments.
- Iterative Revision
- It promotes a process of refining drafts, ensuring that AI-generated text evolves through continuous improvement to meet academic standards.
- Critical Evaluation
- The resource stresses the importance of assessing AI-produced content critically, encouraging analytical thinking and rigorous editing in writing.
Find the full version of this resource in the TextGenEd: Continuing Experiments collection.