LLMs and GenAI in Digital Scholarship

Large Language Models and Generative AI

Large Language Models (LLMs) are a type of generative artificial intelligence designed to understand and generate human-like language. These models – exemplified by systems like OpenAI’s GPT series or Google’s Bard – are trained on datasets of text, learning the patterns of language from the chosen training texts. Essentially, an LLM works by predicting the most likely “next word” or sequence of words in response to a prompt, based on the vast patterns it absorbed during training. This predictive mechanism allows LLMs to produce remarkably fluent sentences and even extended writings that often read as if a human wrote them.  Generative AI refers broadly to AI systems (including LLMs) that can create content – not only text, but also images, music, code, etc. 

How to Use This Guide

This home page is an overview. Use the page tabs on the left-hand side to explore: 

• How LLMs Work
• Critical Literacy within Generative AI
• Ethical and Social Implications of LLMs
• Limitations of Gen AI Responses
• Using LLMs in the Freedman Center
• Basic Prompting Strategies
• Retrieval Augmented Generation
• Fine-Turning LLMs
• Information about the digital scholarship workshop series

Need help? Contact information is available on the left-hand navigation.

 This work is openly licensed via CC BY-NC-SA 4.0. You are free to share (copy and redistribute the material in any medium or format) and adapt (remix, transform, and build upon the material) this material under the following terms:

• You must give appropriate credit, provide a link to the license, and indicate if changes were made.
• You may not use the material for commercial purposes.
• If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.