Skip to Main Content

Artificial Intelligence

A general guide to artificial intelligence.

Citations & Plagiarism

Before using any generative AI, it is strongly advised that you check with your professor. Policies change between classes and professors. It is your responsibility to check what is allowed for your assignment.

The Writing and Multiliteracy Center is the best source for citation guidelines, including those for generative AI.

Uses & Limitations of LLMs

Uses & Limitations of LLMs
Uses Limitations
  • It can be a starting place, but do not rely on it for factual information or research.
  • LLMs and AI are known for producing hallucinations, where the program presents and defends false information as if it were factual.
    • Most LLMs have created citations AND QUOTES to defend its statements, but these can be entirely fabricated.
  • It is not a search engine, but uses vast amounts of data to generate responses that appear to make sense.
  • As a result, LLMs don’t provide the most current information and recent scholarly peer-reviewed articles will not be the most recent research on a topic. You may ask the LLM when that date is, but it is best to go to the developer's notes, if available, to confirm whether its information is up to date.
  • LLMs' privacy policies may allow the creators to sell and profit off of your personal information.
  • Submitting a manuscript to a LLM for writing assistance may violate requirements from journals you wish to publish in or your institution.
  • Anything you submit to an LLM may become a part of the LLM's learning corpus.
  • Discussion starter regarding privacy, intellectual property, research integrity, ethical consumption, and more!

Credit: University of Washington Artificial Intelligence LibGuide

Brainstorming Topics

Try using a generative AI tool, like ChatGPT, to brainstorm your topic. For example, you may be interested in the general topic of the use of AI in health care. This is is a very broad topic and needs to be narrowed a bit. If you're not sure what particular aspect of this topic you might be interested in, you can use ChatGPT to explore facets of this topic. 

Wharton professor, Ethan Mollick, has some useful advice about prompting AI:

"The best way to use AI systems is not to craft the perfect prompt, but rather to use it interactively. Try asking for something. Then ask the AI to modify or adjust its output. Work with the AI, rather than trying to issue a single command that does everything you want. The more you experiment, the better off you are."

Systems like ChatGPT are good at quickly generating text that is hard to distinguish from text created by humans. While impressive, it is important to remember that generative AI does not have the capacity to understand the meaning behind the words it is producing. Because of this, you will want to use these tools as starting (not ending) points in your research process.

Credit: Arizona State University Generative Artificial Intelligence LibGuide

Creating Prompts

Prompts are the instructions used to ask a large language model to perform a task and create an output.  The more specific instructions you can give the generative AI, the better output you're going to get. Prompting generative AI each step of the way guides it to ensure consistency and keeps the AI on topic. 

Whether you are asking a question or providing additional context, you are prompting the language model to perform a task for you. A prompt consists of a few words, a single sentence or paragraphs. Successful prompt crafting influences the quality and relevance of the generated output and the user's satisfaction in the answer. Providing as much instruction and context as you can to a large language model, like ChatGPT, will bring back a more helpful output to the task you've asked.

The CLEAR framework, created by Librarian Leo S. Lo at the University of New Mexico, is a framework to optimize prompts given to generative AI tools. The CLEAR framework describes the most effective prompts as: 

C: Concise: be brief and to the point

L: Logical: maintain a consistent order and logical flow to your instructions

E: Explicit: be clear about your desired output

A: Adaptive: experiment with different prompt structure and phrasing

R: Reflective: critically evaluate the answers you get, then adjust your approach

 

This information comes from the following article. It is highly encouraged to read through this article if you would like to improve your prompt writing. 

Lo, L. S. (2023). The CLEAR path: A framework for enhancing information literacy through prompt engineering. The Journal of Academic Librarianship, 49(4), 102720–. https://doi.org/10.1016/j.acalib.2023.102720

 

Credit: University of Calgary Artificial Intelligence LibGuide