Skip to Main Content

Digital Humanities

This guide is designed to compile resources related to DH tools, methods, and projects, and to help students and faculty get started in DH.

Generative AI Tools: Large Language Models

The below selection provides a summary of a small number of popular LLMs.

ChatGPT

Function (What is it? What does it do?): ChatGPT is an open source conversational AI chatbot developed by OpenAI. It is built from generative pre-trained transformer (GPT) models, a type of LLM.

Login (Does it require an account login?): Required

Cost: Freemium -- a free version is available, with fees required for extra features.

What sets it apart? ChatGPT is credited with the recent "AI boom," having prompted several other developers to release their own LLM chat bots in quick succession after its release. It is easy to use and has a wide range of applications. Chats are archived in the user's account for as long as the account exists. ChatGPT also enables users to share chats via public links.


Claude

Function: Claude is a conversational AI chatbot and text generator developed by Anthropic.

Cost: Freemium.

Login: Required

What sets it apart? Claude allows users to upload large text files, enabling them to analyze a text in various ways. Claude also puts a focus on privacy and ethical AI use. Chats are archived in the user's account for as long as the account exists.


Gemini

Function: Gemini is Google's AI chatbot.

Cost: Freemium.

Login: Google/Gmail account required

What sets it apart? Unlike many of its competitors, the free version of Gemini is connected to the Internet, providing it with access to more up-to-date information. Gemini allows users to upload and analyze text, image, video, and voice files.


Copilot

Function: Github's Copilot tool assists users with generating, updating, fixing, and understanding code.

Cost: Paid plans.

Login: Required

What sets it apart? While other LLMs can provide assistance with code, GitHub Copilot is specifically designed for this purpose and especially adept at it.


Elicit

Function: Elicit is an LLM specifically designed to assist with academic research. 

Cost: Freemium. 

Login: Required

What sets it apart? Elicit is an academic research tool. It parses research inquiries and provides citations of relevant academic sources such as journal articles and books. It is also able to answer questions about these sources. Note: Elicit generally cannot help researchers find primary sources.


Grammarly

Function: Grammarly is designed to help with grammar, clarity, and writing style. 

Cost: Freemium. 

Login: Required

What sets it apart? Grammarly can help you polish your writing and avoid grammatical errors. Use it carefully, however—some plagiarism detection software may flag Grammarly-polished text as plagiarized.

Do's and Don'ts of Large Language Models

Large language models (LLMs) are built on vast amounts of text data. They are trained to understand and generate human language and often take the form of conversational chat bots.

LLMs are powerful tools, but they have limitations. Users should understand what they can and cannot do in order to get the best results from their use. If you ask an LLM to do something it cannot do, it might tell you it doesn't know the answer to your question, but it's just as likely to hallucinate.

What are hallucinations? To put it simply, when a generative AI tool hallucinates, it makes up information that is false, misleading, or nonsensical. It presents this information as fact, so sometimes users don't realize that the output was a hallucination. You can avoid hallucinations by understanding LLMs' capabilities and adhering to the following guidelines:

  • Don't ask an LLM to cite the source of information it has shared with you. Most LLMs are unable to access internet sources in real-time. Asking an LLM to share the source of information it's drawing on may cause a hallucination.
  • Don't ask an LLM how it works. LLMs do not have metacognition, meaning they have no understanding of how they work. In fact, LLMs frequently hallucinate their own capabilities. 
  • Don't ask an LLM to do anything other than produce text or code. LLMs are trained to write sentences, not to know facts.
  • Do provide an LLM with text and ask it questions based on the text. Consider which LLM will be best for this exercise. For example, ChatGPT and Claude are good options because they allow users to upload files.

Be aware that even when you follow the guidelines above, LLMs may hallucinate, make coding mistakes, or provide biased information. LLMs present hallucinated responses as fact. Always be critical of information you've received from an LLM.

Developed from: Tatarian, A. & Scudder, P. (2024, June 3). Beyond science fiction: AI's past, present, & impact on libraries & education [Conference presentation]. 2024 Joint ARCLNEC - NELIG Conference, Worcester, MA, United States.

Generative AI Tools: Image & Media Generators

The following tools for generating AI images and other media content are free or freely available to Merrimack students, faculty, and staff.

For questions or feedback contact the McQuade Library
Call us: 978-837-5177 | Text us:  978-228-2275 | Email us: mcquade@merrimack.edu