Skip to Main Content Libraries

AI Resources

This resource is designed to assist faculty and students in the developing landscape of Artificial Intelligence.

Retrieval-augmented generation (RAG) models pull info from specific knowledge bases such as academic and research databases. They have access to current content where as LLS models such as ChatGTP use dated information and are trained with a much broader content range. 

PROS CONS
You know were the info comes from; it is limited. Cannot breach subscription paywalls. 
Pulls from open access resources.  Students cannot get a broad view of topics.
Fewer "hallucinations."  
Help bridge complex ideas.  
Content is not dated; it uses current info.  

Large Language Models (LLMs) are good at predicting the next word sequence from a very large knowledge base. They are not as accuracy and reliability as RAGs and have a tendency to "hallucinate" and make things up. LLS models such as ChatGTP are more broadly trained.

PROS CONS
good for background research. cannot evaluate credibility of info.
natural conversation and easy to understand. cannot breach paywalls. missing info
easy to ask follow up questions. trained on dated content.
opposing view points are readily available. may "hallucinate" and make things up.
help grasp terminology use in fields of study.  

General LLMs

Willamette University

Willamette University Libraries

Mark O. Hatfield Library
900 State Street.
Salem Oregon 97301
Pacific Northwest College of Art Library
511 NW Broadway.
Portland Oregon 97209