Skip to Main Content

Artificial Intelligence

Text-based generative AI: LLMs

Large language model (LLMs) are the foundation of GAI. LLMs are trained on vast amounts of text to understand existing content and generate original content. They function as chatbots, responding to user prompts by processing natural language in a conversational, human-like way. They can perform a variety of language-based tasks, like generating, summarizing, and translating text.

What are some of the LLMs out there?

  • ChatGPT

    ChatGPT is one of the most talked about generative AI tools available. The current model, ChatGPT 4o, was trained using an enormous dataset made up of text available on the internet. While it is unclear what exactly is in the dataset, OpenAI, the developer of ChatGPT, has stated that the dataset only consists of information through September 2021. 

  • Microsoft CoPilot

    Microsoft Copilot is another OpenAI generated tool (Microsoft is an investor of OpenAI) and uses the same GPT-4 model as ChatGPT. Because it also contains an algorithmic search engine, the information acquired through Copilot is likely to be more accurate than ChatGPT. It also provides sources for some searches, which allows users to see where some of the data came from. As with ChatGPT, the actual dataset used to train this tool is unavailable to the public. You may have heard that sometimes Copilot can generate "weird" or unsettling content. Safeguards have been put in place to limit this type of content generation. 

  • Perplexity

    Perplexity is an AI search engine that also utilizes GPT-4 and is connected to the internet. Users can utilize the "pro" feature to see more detail on how information is gathered and, occasionally, the tool will ask clarifying questions to ensure the generated content is relevant. Perplexity also includes sources and uses a more advanced algorithm for searches to try to provide more "trustworthy" results. 

  • Google Gemini

    Google Gemini is the only tool listed here that requires an account log-in. This tool uses a different type of training model, called the Language Model for Dialogue Applications (LaMDA), to generate responses to user prompts. According to Google, "[t]he language model learns by “reading” trillions of words that help it pick up on patterns that make up human language so it’s good at predicting what might be reasonable responses." The difference in this model from GPT-4 is that it is meant to be more "conversational." Though also tied to the traditional Google search engine, the results tend to be less relevant and reliable than other tools. 

  • Claude
    Claude - free with account sign-up; Claude Pro has a monthly fee. Developed by Anthropic using their model which has a Constitutional AI method to ensure safety and reliability. Responds to image and text prompts, trained on data through April 2024, and is not connected to the Internet.

  • Poe.com
    Poe.com is a free generative AI tool that combines a myriad of generative AI models and tools already out on the market. Here you can base your selection of tool on the task you are trying to accomplish.

What types of things can ChatGPT and other LLMs do?

When asked what it is capable of doing, this is one way ChatGPT has answered:

  • Text generation: This refers to my ability to generate new text based on a given prompt or topic. I can use my understanding of language and my training data to produce sentences, paragraphs, or even longer pieces of text.
  • Text completion: This involves predicting and generating the most likely words or phrases to complete a given sentence or paragraph based on context.
  • Question-solutions: I can provide solutions to questions by identifying the most relevant information from my training data and generating an appropriate response.
  • Summarization: I can summarize longer pieces of text into shorter summaries while retaining the main ideas and important details.
  • Text translation: I can translate text from one language to another, with varying levels of accuracy depending on the language pairs.
  • Conversational AI: This refers to my ability to engage in natural language conversations with humans, responding to prompts and questions in a conversational manner.
  • Sentiment analysis: I can analyze text to determine the overall sentiment or emotion expressed within it.
  • Named entity recognition: I can identify and extract named entities such as people, places, and organizations from text.
  • Part-of-speech tagging: I can identify the part of speech (noun, verb, adjective, etc.) of each word in a given sentence.

Chatbot Content Detection

GPTZero is a classification model that predicts whether a document was written by a large
language model, providing predictions on a sentence, paragraph, and document level. GPTZero was trained on a large, diverse corpus of human-written and AI-generated text, with a focus on English prose.

 ZeroGPT is another chatbot detector that claims to have an algorithm with an accuracy rate of text detection up to 98%.Using  DeepAnalyse™ Technology, ZeroGPT identifies the origins of text that you upload or copy and paste into the content box. ZeroGPT is hoping to develop their chatbot detector further to reduce error rates to under 2%.  

Content Created by Sam Mandani of NYU Libraries: https://guides.nyu.edu/chatgpt. Last Updated: Jan 9, 2025 12:06 PM