ChatGPT is built on a Large Language Model and has been trained on a huge dataset of internet sources. It can quickly and simply generate easy-to-understand responses to any question you throw at it. Responses are only as good as the quality of input data it has been trained on. Its core strength lies in recognizing language patterns—not in reading and analyzing lengthy, scholarly texts. It uses a statistical model to guess, based on probability, the next word, sentence and paragraph to match the context provided by the user.
Many responses with ChatGPT have been found to have fake references. The output is a guess based on an algorithm designed to produce the most plausible or probable, realistic reading language output relevant to the context of the prompt it has been given. Accuracy is not considered in an AI response.
If you choose to use AI in your work:
You should
See below for specific examples. And keep in mind: the MLA template of core elements is meant to provide flexibility in citation. So if you find a rationale to modify these recommendations in your own citations, we encourage you to do so.
Author: We do not recommend treating the AI tool as an author. This recommendation follows the policies developed by various publishers, including the MLA’s journal PMLA.
Title of Source: Describe what was generated by the AI tool. This may involve including information about the prompt in the Title of Source element if you have not done so in the text.
Title of Container: Use the Title of Container element to name the AI tool (e.g., ChatGPT).
Version: Name the version of the AI tool as specifically as possible. For example, the examples in this post were developed using ChatGPT 3.5, which assigns a specific date to the version, so the Version element shows this version date.
Publisher: Name the company that made the tool.
Date: Give the date the content was generated.
Location: Give the general URL for the tool.1
ChatGPT Promt: Describe the symbolism of the green light in the book The Great Gatsby by F. Scott Fitzgerald.
ChatGPT Response: In the novel The Great Gatsby, the green light represents various symbolic meanings, including:
- Hope and Promise: The green light is first seen at the end of Daisy's dock across the water from Gatsby's mansion. For Gatsby, the green light symbolizes his hopes and dreams of being reunited with Daisy and winning her back.
- Illusion and Deception: The green light also symbolizes the illusory nature of the American Dream and Gatsby's belief that he can attain it by acquiring wealth and social status. The green light represents the idea that achieving the Dream is like chasing a mirage or a ghost, something that always remains just out of reach.
- Money and Materialism: The green light also represent the materialistic values of the wealth characters in the novel. For example, the green light serves as a reminder of the wealth and privilege that Daisy and her social circle enjoy, and that Gatsby is striving to attain.
- Envy and Jealousy: The green light also symbolizes Gatsby's envy and jealousy of Tom Buchanan, Daisy's husband, who represents the established wealthy class that Gatsby is trying to break into.
Overall, the green light in The Great Gatsby is a powerful symbol that conveys the themes of hope, illusion, materialism, and envy that runs throughout the novel. It serves as a reminder that the American Dream is often an elusive and unattainable goal,a nd that wealth and status do not necessarily bring happiness or fulfillment.
While the green light in The Great Gatsby might be said to chiefly symbolize four main things: optimism, the unattainability of the American dream, greed, and covetousness (“Describe the symbolism”), arguably the most important—the one that ties all four themes together—is greed.
“Describe the symbolism of the green light in the book The Great Gatsby by F. Scott Fitzgerald” prompt. ChatGPT, 13 Feb. version, OpenAI, 8 Mar. 2023, chat.openai.com/chat.
ChatGPT Promt: In 200 words, describe the symbolism of the green light in The Great Gatsby.
ChatGPT Response: The green light in F. Scott Fitzgerald's The Great Gatsby represents a multitude of symbolic meanings that are essential to the novel's central themes. The lights first appears to the narraotr, Nick Carraway, as a distant and alluring beacon across the water, situated at the end of the dock on the other side of the bay. The light belongs to Daisy Buchanan's mansion and is interpreted by Gatsby as a signal of his love for her.
The green light is a symbol of Gatsby's ambition, longing, and desire for the unattainable. It represents the American Dream, which Gatsby pursues relentlessly, even though it always seems to elude him. The light symbolizes the hope that he can regain Daisy's love and that they can be reunited, just as the green light represents the hope that American offers for those who work hard and strive for success.
The green light is also a symbol of the corruption and decay of the American Dream. It represents the shallowness and emptiness of material wealth and the failure of human relationships to provide genuine satisfaction and happiness. Gatbsy's obsession with the light and his inability to attain it underscores the emptiness of his pursuit of wealth and status and the ultimate futility of his quest.
Overall, the green light is a powerful symbol that embodies many of the novel's central themes and serves as a poignant reminder of the dangers of pursuing an unattainable dream.
ChatGPT Prompt: What scholarly sources were used to generate that description?
ChatGPT Response: As an AI language model, I do not have the ability to conduct research or cite sources independently. However, I can provide a list of scholarly sources related to the symbolism of the green light in The Great Gatsby:
- Bruccoli, Matthew J. "F. Scott Fitzgerald's American Dream." In Critical Essays on F. Scott Fitzgerald's The Great Gatsby, edited by Scott Donaldson, 83-95. G.K. Hall & Co., 1984.
- Johnson, Claudia Durst. "Seeing and Believing: The Great Gatsby." In Understanding The Great Gatsby: A Student Casebook to Issues, Sources, and Historical Documents,e dited by Dalton Gross and MaryJean Gross, 71-87. Greenwood Press, 1998.
- Lee, A. Robert. "Gatsby's Green Light: The Emanation of a Dream." In Twentieth Century Literature 1, no. 1 (1955): 1-6.
- Lydenberg, Robin. "The Symbolic Landscape of The Great Gatsby." In F. Scott Fitzgerald: New Perspectives, edited by Jackson R. Bryer, 153-70. University of Georgia Press, 1982.
These sources and others like them offer detailed analysis and interpretation of the green light as a central symbol in The Great Gatsby.
When asked to describe the symbolism of the green light in The Great Gatsby, ChatGPT provided a summary about optimism, the unattainability of the American dream, greed, and covetousness. However, when further prompted to cite the source on which that summary was based, it noted that it lacked “the ability to conduct research or cite sources independently” but that it could “provide a list of scholarly sources related to the symbolism of the green light in The Great Gatsby” (“In 200 words”).
“In 200 words, describe the symbolism of the green light in The Great Gatsby” follow-up prompt to list sources. ChatGPT, 13 Feb. version, OpenAI, 9 Mar. 2023, chat.openai.com/chat.
Taken from The MLA Style Center
Note that the rules for citing AI in APA are unofficial as the APA team are still navigating and developing the rules for properly citing AI generated work.
The four elements (author, date, title, and source) of an AI Citation:
Author: The author of the model is OpenAI.
Date: The date is the year of the version you used. Following the template in Section 10.10, you need to include only the year, not the exact date. The version number provides the specific date information a reader might need.
Title: The name of the model is “ChatGPT,” so that serves as the title and is italicized in your reference, as shown in the template. Although OpenAI labels unique iterations (i.e., ChatGPT-3, ChatGPT-4), they are using “ChatGPT” as the general name of the model, with updates identified with version numbers.
Source: When the publisher name and the author name are the same, do not repeat the publisher name in the source element of the reference, and move directly to the URL. This is the case for ChatGPT. The URL for ChatGPT is https://chat.openai.com/chat. For other models or products for which you may create a reference, use the URL that links as directly as possible to the source (i.e., the page where you can access the model, not the publisher’s homepage).
If you’ve used ChatGPT or other AI tools in your research, describe how you used the tool in your Method section or in a comparable section of your paper. For literature reviews or other types of essays or response or reaction papers, you might describe how you used the tool in your introduction. In your text, provide the prompt you used and then any portion of the relevant text that was generated in response.
Unfortunately, the results of a ChatGPT “chat” are not retrievable by other readers, and although nonretrievable data or quotations in APA Style papers are usually cited as personal communications, with ChatGPT-generated text there is no person communicating. Quoting ChatGPT’s text from a chat session is therefore more like sharing an algorithm’s output; thus, credit the author of the algorithm with a reference list entry and the corresponding in-text citation.
Example:
When prompted with “Is the left brain right brain divide real or a metaphor?” the ChatGPT-generated text indicated that although the two brain hemispheres are somewhat specialized, “the notation that people can be characterized as ‘left-brained’ or ‘right-brained’ is considered to be an oversimplification and a popular myth” (OpenAI, 2023).
Reference
OpenAI. (2023). ChatGPT (Mar 14 version) [Large language model]. https://chat.openai.com/chat
You may also put the full text of long responses from ChatGPT in an appendix of your paper or in online supplemental materials, so readers have access to the exact text that was generated. It is particularly important to document the exact text created because ChatGPT will generate a unique response in each chat session, even if given the same prompt. If you create appendices or supplemental materials, remember that each should be called out at least once in the body of your APA Style paper.
Example:
When given a follow-up prompt of “What is a more accurate representation?” the ChatGPT-generated text indicated that “different brain regions work together to support various cognitive processes” and “the functional specialization of different regions can change in response to experience and environmental factors” (OpenAI, 2023; see Appendix A for the full transcript).
Reference
OpenAI. (2023). ChatGPT (Mar 14 version) [Large language model]. https://chat.openai.com/chat
The in-text citations and references above are adapted from the reference template for software in Section 10.10 of the Publication Manual (American Psychological Association, 2020, Chapter 10). Although here we focus on ChatGPT, because these guidelines are based on the software template, they can be adapted to note the use of other large language models (e.g., Bard), algorithms, and similar software.
The reference and in-text citations for ChatGPT are formatted as follows:
OpenAI. (2023). ChatGPT (Mar 14 version) [Large language model]. https://chat.openai.com/chat
Let’s break that reference down and look at the four elements (author, date, title, and source):
Author: The author of the model is OpenAI.
Date: The date is the year of the version you used. Following the template in Section 10.10, you need to include only the year, not the exact date. The version number provides the specific date information a reader might need.
Title: The name of the model is “ChatGPT,” so that serves as the title and is italicized in your reference, as shown in the template. Although OpenAI labels unique iterations (i.e., ChatGPT-3, ChatGPT-4), they are using “ChatGPT” as the general name of the model, with updates identified with version numbers.
The version number is included after the title in parentheses. The format for the version number in ChatGPT references includes the date because that is how OpenAI is labeling the versions. Different large language models or software might use different version numbering; use the version number in the format the author or publisher provides, which may be a numbering system (e.g., Version 2.0) or other methods.
Bracketed text is used in references for additional descriptions when they are needed to help a reader understand what’s being cited. References for a number of common sources, such as journal articles and books, do not include bracketed descriptions, but things outside of the typical peer-reviewed system often do. In the case of a reference for ChatGPT, provide the descriptor “Large language model” in square brackets. OpenAI describes ChatGPT-4 as a “large multimodal model,” so that description may be provided instead if you are using ChatGPT-4. Later versions and software or models from other companies may need different descriptions, based on how the publishers describe the model. The goal of the bracketed text is to briefly describe the kind of model to your reader.
Source: When the publisher name and the author name are the same, do not repeat the publisher name in the source element of the reference, and move directly to the URL. This is the case for ChatGPT. The URL for ChatGPT is https://chat.openai.com/chat. For other models or products for which you may create a reference, use the URL that links as directly as possible to the source (i.e., the page where you can access the model, not the publisher’s homepage).
Taken from McAdoo, T. (2023, April 7). American Psychological Association (APA). American Psychological Association. https://apastyle.apa.org/blog/how-to-cite-chatgpt
How to Cite ChatGPT, by McAdoo, T. (2023, April 7).
Effective communication is important no matter who or what you are interacting with. This is true with friends, co-workers, when searching Google, or asking Siri for help, and with generative AI. In this page we'll go over how you can create an effective, comprehensive, and clear prompt to get the most helpful responses from an AI system.
Keep these in mind when writing and following up with AI prompts:
Be specific: Make sure your prompt is clear and you are clearly sharing the type of answer or output that you are looking for
State your intent: Give context as to what this information is needed for to help focus the response to be more helpful for your need.
Correct spelling and grammar: Take time to use proper spelling and grammar.
Direct the output format: Specify what output you want from your response. This can be regarding the format (in a paragraph, in a table, bullet pointed, bold certain terms) or type of response (provide a definition, or explanation, or argument).
Ask follow up questions: Keep asking questions if you didn't get your intended information. You don't need to restate the original question. The more information you provide the more it will understand your need and provide you with the needed information.
Experiment with different phrasing: If needed, consider rephrasing your prompt using different terms or wording.
Prompt for fact-checking: As we've learned generative AI can provide incorrect information, so it is always good to ask it for sources, links, or citations so that the information can be verified elsewhere.
Context + specific information + intent + response format
Context - Provide necessary context or background information in your prompts.
Specific information - Explain what you need and what you are asking the AI system to do.
Intent - Share the purpose or objective of your prompt and what the information will be used for.
Response format - Tell the system what you want the output to look like. Ask for sources or where more information can be found.
Since we know the responses from ChatGPT and other generative AI models can be unreliable, it is always essential to check the credibility of the AI responses. There are a couple ways that you might do this:
MSJC Library has many reference sources you can use in order to verify responses that you have received from ChatGPT and other Generative AI. Use these sources if you plan on using AI so that they can validate/invalidate information that has been fed to you by ChatGPT and other Generative AI. This can help students to understand how AI can be used rather than solely depending on the AI's complete response.