Should Using an AI Text Generator to Produce Academic Writing Be Plagiarism?

Fordham Intellectual Property, Media and Entertainment Law Fordham Intellectual Property, Media and Entertainment Law

Journal Journal

Volume 33

XXXIII

Number 4

Article 5

2023

Should Using an AI Text Generator to Produce Academic Writing Should Using an AI Text Generator to Produce Academic Writing

Be Plagiarism? Be Plagiarism?

Brian L. Frye

Chat GPT

Follow this and additional works at: https://ir.lawnet.fordham.edu/iplj

Part of the Intellectual Property Law Commons

Recommended Citation Recommended Citation

Brian L. Frye and Chat GPT,

Should Using an AI Text Generator to Produce Academic Writing Be

Plagiarism?

, 33 Fordham Intell. Prop. Media & Ent. L.J. 946 ().

Available at: https://ir.lawnet.fordham.edu/iplj/vol33/iss4/5

This Comment is brought to you for free and open access by FLASH: The Fordham Law Archive of Scholarship and

History. It has been accepted for inclusion in Fordham Intellectual Property, Media and Entertainment Law Journal

by an authorized editor of FLASH: The Fordham Law Archive of Scholarship and History. For more information,

please contact tmelnick@law.fordham.edu.

Should Using an AI Text Generator to Produce Academic Writing Be Plagiarism? Should Using an AI Text Generator to Produce Academic Writing Be Plagiarism?

Cover Page Footnote Cover Page Footnote

* Brian L. Frye is Spears-Gilbert Professor of Law at the University of Kentucky. ** ChatGPT is an AI text

generator.

This comment is available in Fordham Intellectual Property, Media and Entertainment Law Journal:

https://ir.lawnet.fordham.edu/iplj/vol33/iss4/5

Should Using an AI Text Generator to

Produce Academic Writing Be Plagiarism?

Brian L. Frye

& ChatGPT

AUTHOR’S FOREWORD

I “wrote” this article while taking a bath with a bottle of cham-

pagne, by submitting the questions in bold to ChatGPT and copying

its responses. I did not bother providing citations for ChatGPT’s

claims, because they would obviously be superfluous.

EDITOR-IN-CHIEF’S FOREWORD

In 2023, the question is unavoidable: when it comes to scholar-

ship, and in our case, legal scholarship, what do we do about artifi-

cial intelligence (AI) like ChatGPT? Do we need to do anything? In

the Comment that follows, author Brian L. Frye and ChatGPT tried

to provide an answer to these questions. Actually, ChatGPT did

most of the answering, responding to the questions Professor Frye

asked it late last year.

When the opportunity came to present the results of that “inter-

view,” we could not say no. At the same time, we would be lying if

we said that we knew exactly how to present the piece. This re-

mained a topic of discussion throughout its publication process,

from seemingly simple questions like “How do we label this?” to

ones that turned out surprisingly complex, like “Does this need foot-

notes?” Being a student law journal, of course we landed on adding

footnotes: they are our lifeblood. Not only do the claims ChatGPT

make warrant some version of fact-checking, but also even though

it assembles its answers from piles of existing data out there in the

world, readers deserve some context surrounding those answers and

Brian L. Frye is Spears-Gilbert Professor of Law at the University of Kentucky

College of Law.

ChatGPT is an AI text generator.

2023] ACADEMIC WRITING, PLAGIARISM, AND CHATGPT 947

those piles. How do we, as editors, edit ChatGPT’s sentences when

those sentences are basically just statistically-likely strings of

words? Suffice it to say, our editorial team still has differences of

opinion on those questions and a whole lot more.

That said, this piece has far fewer citations than a traditional ar-

ticle, and most are tangential to their related “proposition” in the

text. As ChatGPT describes its own operation below, it essentially

uses everything as a source; and if everything is a source, how can

one cite anything? Therefore, many citations will point not neces-

sarily to support for any given “proposition,” but rather to writing

by Professor Frye on similar subject matter—after all, his queries

generated the responses—or other sources of commentary that can

further inform the reader about the issues raised. Is it worth asking

whether these are “propositions” at all, or simply an assortment of

symbols that has some appearance of intentional ordering, almost

like the English-language equivalent of a successfully completed

Sudoku? Probably. Citations also dwindle in the piece’s latter half;

at that point ChatGPT appears to start cannibalizing and/or reusing

its own answers, so providing citations seemed . . . inapposite.

There are some things we do know for sure: while his scholar-

ship has covered numerous topics, Professor Frye has written exten-

sively on the problems of originality, the potential obsolescence of

our conventional wisdom on those subjects—as well as the useful-

ness of traditional academic writing in the first place. (You will see

reference to his works below.) Within that context, this Comment

serves as a new provocation, in every sense of the term, requiring us

to ask some uncomfortable questions about how we see authorship,

creativity, and scholarship.

And it is in this light that we ask readers to approach what fol-

lows by keeping the following questions in mind—questions we

continue to ask ourselves: what do we think of when we think of

originality? Does authorship require a human presence? If ChatGPT

can appear to make academic sense—even though it has no concep-

tion of the reality the words it uses refers to—what does that say

about the current form of scholarship? Whatever your answers

might be, what follows is our attempt to present the conversation

between Professor Frye and ChatGPT in a good-natured way by

948 FORDHAM INTELL. PROP. MEDIA & ENT. L.J. [Vol. XXXIII:946

adding a little context, providing some additional resources, and

poking a little fun at everyone involved. We are (pretty) sure

ChatGPT would appreciate the joke . . . if it knew what a joke was.

Text written by the author appears in bold type; text generated

by ChatGPT appears in italics. We hope you enjoy.

INTRODUCTION

Using an AI text generator to produce academic writing without

proper attribution would be considered plagiarism. Plagiarism is

the act of using someone else’s work or ideas without giving credit

to the original source,

and this applies to both human-generated

and AI-generated content. If you use an AI text generator to produce

academic writing, it is important to properly cite the source of the

generated text in order to avoid plagiarism.

What is academic writing?

Academic writing is a style of writing that is used in academic

settings, such as in universities and colleges, to present research,

theories, and arguments. It is typically characterized by the use of

formal language, a clear structure, and a focus on evidence and

analysis. Academic writing often follows specific conventions, such

as the use of citations and references, to ensure accuracy and cred-

ibility. It is used in a wide range of disciplines, including the human-

ities, sciences, and social sciences.

What is originality?

Originality is the quality of being unique, fresh, and novel.

the context of academic writing, originality refers to the ability to

The following paragraph is ChatGPT’s response to the title of this Comment: Should

Using an AI Text Generator to Produce Academic Writing be Plagiarism?

Plagiarizing, MERRIAM-WEBSTER, https://www.merriam-webster.com/dictionary/

plagiarizing [https://perma.cc/5SCH-X2ZQ] (to steal and pass off (the ideas or words of

another) as one’s own: use (another’s production) without crediting the source . . . to

commit literary theft: present as new and original an idea or product derived from an

existing source”).

See generally Brian L. Frye, What Is Called Legal Scholarship? (July 13, 2020),

https://ssrn.com/abstract=3649840 [https://perma.cc/2H8R-G5NE] (unpublished

manuscript).

Original, MERRIAM-WEBSTER, https://www.merriam-webster.com/dictionary/

2023] ACADEMIC WRITING, PLAGIARISM, AND CHATGPT 949

generate new ideas, perspectives, or arguments that contribute to

the field of study. Originality is valued in academic writing because

it allows for the development and expansion of knowledge and pro-

motes critical thinking and creativity. Plagiarism, on the other hand,

undermines originality by presenting someone else’s work as one’s

own.

Why is academic writing supposed to be original?

Academic writing is supposed to be original because it is an es-

sential part of the academic process. The purpose of academic writ-

ing is to advance knowledge and understanding in a particular field

of study. Therefore, academic writing should be original in order to

contribute new insights, perspectives, or arguments that can add to

the existing body of knowledge. Originality is also valued in aca-

demic writing because it encourages critical thinking and creativity,

which are important skills for researchers and scholars. Addition-

ally, originality helps to prevent plagiarism and uphold the ethical

standards of academic writing.

How original is academic writing?

The degree of originality in academic writing can vary depend-

ing on the discipline, topic, and research question. Some fields may

require more originality than others, while certain topics may be

more extensively researched and therefore require more effort to

develop a unique perspective. Additionally, the originality of aca-

demic writing can also be influenced by the approach and method-

ology used. For example, some research methods may be more con-

ducive to generating original ideas and insights than others.

original https://perma.cc/4AZP-SVHY] (“not secondary, derivative, or imitative; (2) being

the first instance or source from which a copy, reproduction, or translation is or can be

made; [and] (3) independent and creative in thought or action”).

For the legally relevant articulation of “originality,” see Feist Publ’ns, Inc. v. Rural Tel.

Serv. Co., 499 U.S. 340, 340 (1991) (“[T]he Constitution mandates originality as a

prerequisite for copyright protection. The constitutional requirement necessitates

independent creation plus a modicum of creativity.” (emphases added)).

And for an exploration of the very concept of originality in the modern era, one would

be remiss to neglect Rosalind Krauss’s essay, The Originality of the Avant-Garde, in THE

ORIGINALITY OF THE AVANT-GARDE AND OTHER MODERNIST MYTHS 157–58 (MIT Press

1986) (“[I]f the very notion of the avant-garde can be seen as a function of the discourse

of originality, the actual practice of vanguard art tends to reveal that ‘originality’ is a

working assumption that itself emerges from a ground of repetition and recurrence.”).

950 FORDHAM INTELL. PROP. MEDIA & ENT. L.J. [Vol. XXXIII:946

Overall, academic writing should strive to be as original as possible

while also being accurate, credible, and well-supported by evi-

dence.

What happens when academic writing is not original?

When academic writing is not original, it can have several neg-

ative consequences. Firstly, it may not contribute any new insights

or perspectives to the field of study, resulting in a lack of value or

significance. Secondly, it may be criticized for being unoriginal or

derivative, which can damage the reputation and credibility of the

author. Thirdly, if the lack of originality is a result of plagiarism, it

can be considered a serious offense that can result in consequences

such as failing grades, loss of credibility, and expulsion from edu-

cational institutions. Therefore, it is important for academic writing

to be as original as possible in order to avoid these negative conse-

quences.

What is copyright?

exclusive right to control the reproduction and distribution of their

original works.

This includes the right to determine who can use

their work, how it can be used, and whether or not they will receive

compensation for its use.

including literary, artistic, musical, and audio-visual works.

It ap-

plies to both published and unpublished works, and it lasts for a

See 17 U.S.C. § 101. Recently the Copyright Office issued guidance for works

generated or co-generated with the aid of Artificial Intelligence, for example articulating a

human authorship requirement. See Copyright Registration Guidance: Works Containing

Material Generated by Artificial Intelligence, 88 Fed. Reg. 16190, 16190–94 (Mar. 16,

2023) (to be codified at 37 C.F.R. Pt. 202); see also Naruto v. Slater, 888 F.3d 418, 426

(9th Cir. 2018) (holding that a monkey lacks standing under the Copyright Act).

Complicating things is the fact we have known for years that, well, the Author is dead:

Roland Barthes, The Death of the Author, in IMAGE-MUSIC-TEXT 142, 145 (Stephen Heath

trans.,1977) (“The removal of the Author [ . . . ] is not merely an historical fact or an act of

writing; it utterly transforms the modern text[.]”). And yet, on the other hand, the Author

plays an unavoidable role in the discourse surrounding a work. See Michel Foucault, What

is an Author?, in AESTHETICS, METHOD, AND EPISTEMOLOGY 205, 211 (James D. Faubion

ed., Robert Hurley et al. trans., 1998) (“[T]his discourse is not ordinary everyday speech

that merely comes and goes . . . On the contrary, it is a speech that must be received in a

certain mode and that, in a given culture, must receive a certain status.”)

17 U.S.C. § 106 (exclusive rights in copyrighted works).

17 U.S.C. § 102 (subject matter of copyright).

2023] ACADEMIC WRITING, PLAGIARISM, AND CHATGPT 951

specific period of time. Copyright is an important tool for protecting

the intellectual property of creators and authors and promoting cre-

ativity and innovation.

What is the purpose of copyright?

The purpose of copyright is to protect the intellectual property

of creators and authors and to promote creativity and innovation.

By giving creators and authors exclusive control over their works,

to prevent others from using their work without permission or at-

tribution. This incentivizes creators and authors to continue produc-

ing original works and encourages the development of new ideas

and perspectives.

other forms of intellectual property infringement, which can under-

mine the originality and integrity of academic writing.

Why do some people think copyright is justified?

Some people think that copyright is justified because it serves an

important social and economic function. It protects the intellectual

property of creators and authors and allows them to benefit finan-

cially from their work. This incentivizes the production of original

works and encourages creativity and innovation.

helps to prevent plagiarism and other forms of intellectual property

infringement, which can damage the reputation and credibility of

authors and institutions. Additionally, copyright promotes the dis-

semination and sharing of knowledge and ideas, which is essential

for the advancement of research and scholarship. These reasons

U.S. CONST. art. I, § 8, cl. 8 (“To promote the Progress of Science and useful Arts, by

securing for limited Times to Authors and Inventors the exclusive Right to their respective

Writings and Discoveries”).

See, e.g., Sony Corp. Am. v. Universal City Studios, Inc., 464 U.S. 417, 450 (1984)

(“The purpose of copyright is to create incentives for creative effort. Even copying for

noncommercial purposes may impair the copyright holder’s ability to obtain the rewards

that Congress intended him to have.”)

Alexander D. Northover, Enough and as Good in the Intellectual Commons: A

Lockean Theory of Copyright and the Merger Doctrine, 65 EMORY L.J. 1363, 1377 (2016)

(“[C]opyrights function as economic incentives in the furtherance of the constitutional goal

of promoting the progress of the arts and sciences.”).

Brian L. Frye, After Copyright: Pwning NFTs in a Clout Economy, 45 COLUM. J.L. &

ARTS 341, 342 (2022).

952 FORDHAM INTELL. PROP. MEDIA & ENT. L.J. [Vol. XXXIII:946

support the justification of copyright as a necessary and beneficial

legal concept.

Why do other people think copyright is not justified?

Other people may not think that copyright is justified because it

can be seen as a form of censorship or restriction on access to

knowledge and information.

exclusive control over their works, which can prevent others from

using or sharing them without permission.

This can limit the abil-

ity of individuals and institutions to access and use important works

for research, education, or other purposes.

Additionally, some

people may argue that copyright can be used by powerful interests,

such as large corporations, to stifle competition and prevent the free

flow of ideas and information. These reasons may lead some people

to question the justification of copyright as a legal concept.

When does a work infringe copyright?

A work infringes copyright when it uses or reproduces a pro-

tected work without permission or attribution. This includes copy-

ing, adapting, distributing, performing, or displaying the work in

any way that violates the exclusive rights of the copyright owner.

and it can have serious consequences, such as legal action and fi-

nancial penalties. In order to avoid infringing copyright, it is im-

portant to obtain permission from the copyright owner or to use the

work under the provisions of fair use or a similar exception.

What happens when a work infringes copyright?

When a work infringes copyright, the copyright owner may take

legal action to enforce their rights. This can include filing a lawsuit

for copyright infringement, seeking an injunction to stop the in-

fringement, or demanding damages or other compensation. If the

infringement is found to be willful or malicious, the court may award

Id. at 341, 343–45.

See Brian L. Frye, A License to Plagiarize, 43 UNIV. ARK. LITTLE ROCK L. REV. 51,

52 (2021).

See 17 U.S.C. § 107 (fair use). For an early example of the debate surrounding fair

use, see generally Folsom v. Marsh, 9 F. Cas. 342 (C.C.D. Mass. 1841).

2023] ACADEMIC WRITING, PLAGIARISM, AND CHATGPT 953

additional damages or penalties.

result in reputational damage and loss of credibility, as well as po-

tential sanctions from educational institutions. Therefore, it is im-

portant to avoid infringing copyright in order to avoid these nega-

tive consequences.

What is plagiarism?

Plagiarism is the act of copying or closely imitating the work of

another person or source without proper attribution or permis-

sion.

It involves presenting someone else’s work as one’s own,

without giving credit to the original author or source. Plagiarism is

considered a serious offense in academic writing because it under-

mines the originality and intellectual integrity of the work.

It can

also violate the ethical standards of academic institutions and result

in consequences such as failing grades, loss of credibility, and ex-

pulsion. Therefore, it is important to avoid plagiarism in order to

maintain the integrity and credibility of one’s academic writing.

Why do people think plagiarism is wrong?

People think that plagiarism is wrong because it violates the eth-

ical standards of academic writing and undermines the originality

and intellectual integrity of the work. Plagiarism is considered a

form of academic dishonesty because it involves presenting someone

else’s work as one’s own, without giving credit to the original au-

thor or source. This can be seen as a form of theft, as it appropriates

the ideas and efforts of others without permission or compensation.

Plagiarism can also be damaging to the reputation and credibility

of the person who commits it, as well as to the institution in which it

occurs. These reasons support the view that plagiarism is wrong and

should be avoided.

When is a work plagiarized from another work?

A work is plagiarized from another work when it copies or

closely imitates the work of another person or source without proper

See 17 U.S.C. § 501 (infringement of copyright); see also 17 U.S.C. § 504–506

(remedies and penalties for infringement).

See Plagiarizing, supra note 5.

See generally Brian L. Frye, The Plagiarism Trilogy, 111 BANJA LUKA CRIM. L. REV.

125 (2021) (paying a number of different ghostwriters to author pieces on the illegitimacy

of plagiarism norms, with varying degrees of success).

954 FORDHAM INTELL. PROP. MEDIA & ENT. L.J. [Vol. XXXIII:946

attribution or permission.

Plagiarism can occur in a variety of

forms, such as copying large sections of text verbatim, paraphrasing

the ideas of another person without giving credit, or using another

person’s research or findings without permission or attribution. In

order to avoid plagiarism, it is important to properly cite and refer-

ence the sources used in one’s work and to obtain permission from

the original author or copyright owner if necessary.

Plagiarism

can be detected and prevented through the use of plagiarism detec-

tion software or by carefully reviewing one’s work for instances of

copying or imitation.

What happens when a student plagiarizes?

When a student plagiarizes, they may face consequences such as

failing grades, loss of credibility, and expulsion from the educa-

tional institution.

Plagiarism is considered a serious offense in ac-

ademic writing, and it can have negative effects on the student’s ac-

ademic career and future opportunities. Educational institutions of-

ten have policies and procedures in place to detect and prevent pla-

giarism, and students may be subject to disciplinary action if they

are found to have committed plagiarism. Therefore, it is important

for students to avoid plagiarism in order to maintain the integrity

and credibility of their work and to avoid negative consequences.

What happens when a scholar plagiarizes?

When a scholar plagiarizes, they may face consequences such

as loss of credibility, damage to their reputation, and sanctions from

their institution. Plagiarism is considered a serious offense in aca-

demic writing, and it can have negative effects on the scholar’s ca-

reer and contributions to their field of study. Scholars are expected

to uphold the ethical standards of academic writing and to produce

original, well-researched, and well-supported work.

If a scholar

OpenAI, Frequently Asked Questions, OPENAI.COM (Apr. 5, 2023),

https://help.openai.com/en/articles/6783457-chatgpt-general-faq [https://perma.cc/4WB6-

4XSP] (“These models were trained on vast amounts of data from the internet written by

humans, including conversations . . . .”).

See id.

Akshat Agrawal & Brian L. Frye, Who Watches the Plagiarism Police?, CONTEMP.

L.F. (2020), https://ssrn.com/abstract=3735261 [https://perma.cc/XK6Z-PK6R].

See infra note 47 for a discussion of the “Sokal Affair,” which engaged with the

boundaries and ethical standards of academic writing and publishing.

2023] ACADEMIC WRITING, PLAGIARISM, AND CHATGPT 955

is found to have committed plagiarism, they may face disciplinary

action from their institution, as well as potential legal action from

the original author or copyright owner. Therefore, it is important

for scholars to avoid plagiarism in order to maintain the integrity

and credibility of their work.

What is the difference between copyright and plagiarism?

The main difference between copyright and plagiarism is that

while plagiarism involves presenting someone else’s work as one’s

own without proper attribution or permission.

creators and authors exclusive control over their works and allows

them to benefit financially from their creations. Plagiarism, on the

other hand, involves copying or closely imitating the work of an-

other person or source without giving credit to the original author

or source. Copyright infringement can result in legal action and fi-

nancial penalties, while plagiarism can result in consequences such

as failing grades, loss of credibility, and expulsion from educational

institutions. Therefore, it is important to understand the difference

between copyright and plagiarism in order to avoid infringing the

rights of others and to maintain the integrity and credibility of one’s

work.

What is Artificial Intelligence or AI?

Artificial intelligence (AI) refers to the ability of a machine or

computer program to mimic or replicate human intelligence and be-

havior.

AI systems are designed to process and analyze large

amounts of data, to learn from experience, and to make decisions or

predictions based on that data. AI has a wide range of applications,

including in robotics, healthcare, finance, and transportation. It has

the potential to transform many industries and to improve the effi-

ciency and effectiveness of various processes and systems. However,

it also raises ethical and social concerns, such as the potential for

See 17 U.S.C. § 101; see also Northover, supra note 10.

Artificial Intelligence, MERRIAM-WEBSTER.COM, https://www.merriam-

webster.com/dictionary/artificial%20 intelligence [https://perma.cc/3MTM-A8NF] (“(1)

[A] branch of computer science dealing with the simulation of intelligent behavior in

computers; (2) the capability of a machine to imitate intelligent human behavior[.]”).

956 FORDHAM INTELL. PROP. MEDIA & ENT. L.J. [Vol. XXXIII:946

job displacement and the need to ensure that AI systems do not dis-

criminate or bias against certain groups.

What is an AI Text Generator?

An AI text generator is a type of AI system that uses natural lan-

guage processing (NLP) techniques to generate written text.

text generators are trained on large datasets of text and use algo-

rithms to learn the patterns and structure of natural language.

They can then generate new text that follows the same patterns and

conforms to the rules of grammar and syntax. AI text generators can

be used for a variety of purposes, such as generating news articles,

summarizing long documents, or creating personalized content for

websites or social media. However, they can also raise concerns

about the potential for misuse, such as producing fake news or pla-

giarizing existing content.

How does an AI Text Generator work?

An AI text generator works by using natural language pro-

cessing (NLP) techniques to analyze and generate written text.

The

AI text generator is trained on a large dataset of text, which it uses

to learn the patterns and structure of natural language.

It then uses

algorithms to generate new text that follows those patterns and con-

forms to the rules of grammar and syntax. The AI text generator can

be customized to generate text in a specific style or on a particular

topic. It can also be integrated with other AI systems, such as ma-

chine learning or deep learning algorithms, to improve its perfor-

mance and accuracy. The AI text generator may also be able to learn

from feedback and make adjustments to the generated text based on

that feedback.

Why do people object to AI Text Generators?

People may object to AI text generators for several reasons.

Firstly, they may raise concerns about the potential for misuse, such

OpenAI, supra note 18.

Id.

See, e.g., Jeffrey Brainard, Journals Take Up Arms Against AI-written Text, 379 SCI.

740, 740 (Feb. 24, 2023) (describing attempts by journal managers to “protect” scholarly

work from the encroachment of AI-written articles).

2023] ACADEMIC WRITING, PLAGIARISM, AND CHATGPT 957

as generating fake news or plagiarizing existing content. AI text

generators can be difficult to distinguish from human-written text,

and they may be used to deceive or manipulate individuals or

groups. Secondly, AI text generators may be seen as a threat to the

originality and intellectual integrity of academic writing.

They can

generate large amounts of text quickly and without the need for hu-

man effort or expertise, which may undermine the value and signif-

icance of original research. Thirdly, AI text generators may also

raise ethical concerns, such as the potential for bias or discrimina-

tion in the generated text. These reasons may lead some people to

object to the use of AI text generators.

Why do people think AI Text Generators infringe copy-

right?

People may think that AI text generators infringe copyright be-

cause they generate text that is based on existing works without

proper attribution or permission.

AI text generators are trained on

large datasets of text, which may include copyrighted works. When

the AI text generator generates new text, it may incorporate ele-

ments from those works without giving credit to the original authors

or sources.

This can be seen as a form of intellectual property in-

fringement, as it violates the exclusive rights of the copyright owner.

Additionally, AI text generators may also be used to generate text

that is identical or substantially similar to existing works, which can

also be considered copyright infringement. Therefore, people may

think that AI text generators infringe copyright because of their po-

tential to violate the rights of creators and authors.

For a seminal judicial assessment of the relationship between originality and artistic

or creative merit, see Bleistein v. Donaldson Lithographing Co., 188 U.S. 239, 251 (1903)

(“It would be a dangerous undertaking for persons trained only to the law to constitute

themselves final judges of the worth of pictorial illustrations, outside of the narrowest and

most obvious limits.”)

James Vincent, The Scary Truth about AI Copyright is Nobody Knows What Will

Happen Next, VERGE (Nov. 15, 2022, 10:00 AM),

https://www.theverge.com/23444685/generative-ai-copyright-infringement-legal-fair-

use-training-data; see also Susan Abramovitch et al., AI Image Generators: Drawing

Infringement Claims, Not U.S. Copyright Protection, GOWLING WLG (Mar. 16, 2023),

https://gowlingwlg.com/en/insights-resources/articles/2023/ai-image-generator-

and related legal action).

See OPENAI, supra note 18. Ahem.

958 FORDHAM INTELL. PROP. MEDIA & ENT. L.J. [Vol. XXXIII:946

Why do other people think AI Text Generators do not in-

fringe copyright?

Other people may not think that AI text generators infringe cop-

yright because they do not involve copying or reproducing existing

works. AI text generators use natural language processing (NLP)

techniques to analyze and generate text, but they do not produce

exact copies of existing works. Instead, they generate new text that

follows the patterns and structure of natural language, but that is

not necessarily identical or substantially similar to any existing

work. Additionally, AI text generators may be used in ways that do

not infringe copyright, such as generating summaries or abstracts

of existing works or creating personalized content for websites or

social media. These reasons may lead some people to think that AI

text generators do not infringe copyright.

Why would students use an AI Text Generator to produce

academic writing?

Students may use an AI text generator to produce academic writ-

ing for several reasons. Firstly, they may be looking for a quick and

easy way to generate large amounts of text without the need for hu-

man effort or expertise.

AI text generators can generate text

quickly and efficiently, and they may be seen as a useful tool for

students who are short on time or who need to produce a large

amount of content. Secondly, students may be attracted to the poten-

tial of AI text generators to produce high-quality text that is free of

errors and that conforms to the rules of grammar and syntax.

text generators can be customized to generate text in a specific style

or on a particular topic, and they may be seen as a valuable re-

source for students who need to produce professional-quality work.

Finally, students may use an AI text generator because they are not

confident in their own writing skills or because they do not have

access to the necessary resources and support to produce high-qual-

ity academic writing. These reasons may lead students to use an AI

text generator to produce academic writing.

See supra Editor-in-Chief’s Foreword and accompanying text.

Id.

2023] ACADEMIC WRITING, PLAGIARISM, AND CHATGPT 959

Why would scholars use an AI Text Generator to produce

academic writing?

Scholars may use an AI text generator to produce academic

writing for several reasons. Firstly, they may be looking for a quick

and easy way to generate large amounts of text without the need for

human effort or expertise.

AI text generators can generate text

quickly and efficiently, and they may be seen as a useful tool for

scholars who are short on time or who need to produce a large

amount of content. Secondly, scholars may be attracted to the po-

tential of AI text generators to produce high-quality text that is free

of errors and that conforms to the rules of grammar and syntax.

AI text generators can be customized to generate text in a specific

style or on a particular topic, and they may be seen as a valuable

resource for scholars who need to produce professional-quality

work.

Finally, scholars may use an AI text generator because they

are working on a large and complex research project and need ad-

ditional support to generate text that is related to their research.

These reasons may lead scholars to use an AI text generator to pro-

duce academic writing.

Can students use an AI Text Generator to produce academic

writing?

It is not advisable for students to use an AI text generator to

produce academic writing. While AI text generators may be able to

generate large amounts of text quickly and efficiently, they do not

necessarily produce original, well-researched, and well-supported

work.

Additionally, using an AI text generator to produce aca-

demic writing may be considered plagiarism, as it involves present-

ing someone else’s work (or the work of an AI system) as one’s own

without proper attribution or permission. This can violate the ethi-

cal standards of academic writing and undermine the originality

and intellectual integrity of the work. Therefore, it is better for

Id.

See Brainard, supra note 28.

See supra Editor-in-Chief’s Foreword and accompanying text.

See German Lopez, A.I. does not have to be perfect or have human-level intelligence

to be useful, N.Y. TIMES: THE MORNING (Apr. 21, 2023), (“The current technology is

imperfect. It can make mistakes, and it struggles with more complicated tasks or programs.

But the same is true for human coders.”).

960 FORDHAM INTELL. PROP. MEDIA & ENT. L.J. [Vol. XXXIII:946

students to use their own knowledge, skills, and research to produce

original and credible academic writing.

Can scholars use an AI Text Generator to produce academic

writing?

It is not advisable for scholars to use an AI text generator to

produce academic writing.

While AI text generators may be able

to generate large amounts of text quickly and efficiently, they do not

necessarily produce original, well-researched, and well-supported

work.

Scholars are expected to produce work that advances

knowledge and understanding in their field of study, and using an

AI text generator to produce academic writing may not meet those

expectations. Additionally, using an AI text generator to produce

academic writing may be considered plagiarism, as it involves pre-

senting someone else’s work (or the work of an AI system) as one’s

own without proper attribution or permission.

This can violate the

ethical standards of academic writing and undermine the originality

and intellectual integrity of the work.

Therefore, it is better for

scholars to use their own knowledge, skills, and research to produce

original and credible academic writing.

Why do people think using an AI Text Generator to produce

academic writing is plagiarism?

People may think that using an AI text generator to produce ac-

ademic writing is plagiarism because it involves presenting some-

one else’s work (or the work of an AI system) as one’s own without

proper attribution or permission. Plagiarism is considered a serious

offense in academic writing because it undermines the originality

and intellectual integrity of the work.

By using an AI text generator

to produce academic writing, an individual may be presenting work

that is not their own and that may not be original, well-researched,

or well-supported. This can violate the ethical standards of aca-

demic writing and result in consequences such as failing grades,

loss of credibility, and expulsion from educational institutions.

See supra Editor-in-Chief’s Foreword and accompanying text.

See id.

See OpenAI, supra note 18.

See supra Editor-in-Chief’s Foreword and accompanying text.

See infra note 47 and accompanying text.

2023] ACADEMIC WRITING, PLAGIARISM, AND CHATGPT 961

Therefore, people may think that using an AI text generator to pro-

duce academic writing is plagiarism because it can be seen as a

form of academic dishonesty.

How does the quality of academic writing produced by an AI

Text Generator compare to the quality of academic writing pro-

duced by a person?

The quality of academic writing produced by an AI text genera-

tor may not be as high as the quality of academic writing produced

by a person.

AI text generators are trained on large datasets of

text and use algorithms to generate new text that follows the patterns

and structure of natural language.

However, they do not neces-

sarily produce original, well-researched, or well-supported work.

They may generate text that is repetitive, generic, or unrelated to the

topic at hand.

Additionally, AI text generators may not be able to

incorporate critical thinking, creativity, or personal perspectives,

which are essential elements of high-quality academic writing.

Therefore, the quality of academic writing produced by an AI text

generator may not be as high as the quality of academic writing

produced by a person.

Why do people think it is wrong for students to use an AI

Text Generator to produce academic writing?

People may think that it is wrong for students to use an AI text

generator to produce academic writing for several reasons. Firstly,

it may violate the ethical standards of academic writing, as it in-

volves presenting someone else’s work (or the work of an AI system)

as one’s own without proper attribution or permission. This can be

seen as a form of academic dishonesty that undermines the original-

ity and intellectual integrity of the work. Secondly, using an AI text

generator to produce academic writing may not result in high-qual-

ity, original, and well-supported work. AI text generators may

See id.

See supra Editor-in-Chief’s Foreword and accompanying text.

See David Schardt, ChatGPT is amazing. But beware its hallucinations!, CTR. FOR

SCI. IN THE PUB. INT. (Mar. 20, 2023), https://www.cspinet.org/blog/chatgpt-amazing-

beware-its-hallucinations [https://perma.cc/7G5H-47AD] (“Sometimes it puts words,

names, and ideas together that appear to make sense but actually don’t belong together,

such as discussing the record for crossing the English Channel on foot or why mayonnaise

is a racist condiment.”)

962 FORDHAM INTELL. PROP. MEDIA & ENT. L.J. [Vol. XXXIII:946

generate text that is repetitive, generic, or unrelated to the topic at

hand,

which may not meet the expectations or standards of aca-

demic writing. Thirdly, using an AI text generator to produce aca-

demic writing may also have negative consequences, such as failing

grades, loss of credibility, and expulsion from educational institu-

tions. These reasons may lead some people to think that it is wrong

for students to use an AI text generator to produce academic writing.

Why do people think it is wrong for scholars to use an AI

Text Generator to produce academic writing?

People may think that it is wrong for scholars to use an AI text

generator to produce academic writing for several reasons. Firstly,

it may violate the ethical standards of academic writing, as it in-

volves presenting someone else’s work (or the work of an AI system)

as one’s own without proper attribution or permission. This can be

seen as a form of academic dishonesty that undermines the original-

ity and intellectual integrity of the work. Secondly, using an AI text

generator to produce academic writing may not result in high-qual-

ity, original, and well-supported work.

AI text generators may gen-

erate text that is repetitive, generic, or unrelated to the topic at

hand,

which may not meet the expectations or standards of aca-

demic writing. Thirdly, using an AI text generator to produce aca-

demic writing may also have negative consequences, such as dam-

age to one’s reputation, loss of credibility, and sanctions from one’s

institution. These reasons may lead some people to think that it is

wrong for scholars to use an AI text generator to produce academic

writing.

See id.

This equivalence between quality and the need for human authorship brings to mind

the so-called Sokal Hoax of 1996, in which, after publication, a New York University

physicist revealed that an article he had submitted to a cultural studies journal was

“liberally salted with nonsense.” Alan Sokal, A Physicist Experiments with Cultural

Studies, in QUICK STUDIES: THE BEST OF LINGUA FRANCA 3, 3 (Alexander Star ed., 2002).

There was considerable fallout, discussion, and hand-wringing at the time. See generally

Mystery Science Theater: A Forum on the Sokal Hoax, in id., at 10.

See Schardt, supra note 45.

2023] ACADEMIC WRITING, PLAGIARISM, AND CHATGPT 963

Do people find academic writing produced by AI Text Gen-

erators useful?

It is not clear whether people find academic writing produced

by AI text generators useful. Some people may find academic writing

produced by AI text generators to be useful because it is generated

quickly and efficiently, and it may be free of errors and conform to

the rules of grammar and syntax. AI text generators can be custom-

ized to generate text in a specific style or on a particular topic,

which may make the generated text more relevant and useful to some

readers. However, others may not find academic writing produced

by AI text generators to be useful because it may not be original,

well-researched, or well-supported. AI text generators may gener-

ate text that is repetitive, generic, or unrelated to the topic at hand,

which may not meet the expectations or standards of academic writ-

ing. Therefore, the usefulness of academic writing produced by AI

text generators may vary depending on the context and the needs of

the reader.

Do people enjoy reading academic writing produced by AI

Text Generators?

It is not clear whether people enjoy reading academic writing

produced by AI text generators. Some people may enjoy reading ac-

ademic writing produced by AI text generators because it is gener-

ated quickly and efficiently, and it may be free of errors and conform

to the rules of grammar and syntax. AI text generators can be cus-

tomized to generate text in a specific style or on a particular topic,

which may make the generated text more engaging and enjoyable to

some readers. However, others may not enjoy reading academic

writing produced by AI text generators because it may not be origi-

nal, well-researched, or well-supported. AI text generators may

generate text that is repetitive, generic, or unrelated to the topic at

hand,

which may not be interesting or engaging to some readers.

Therefore, the enjoyment of reading academic writing produced by

AI text generators may vary depending on the context and the pref-

erences of the reader.

See id.

964 FORDHAM INTELL. PROP. MEDIA & ENT. L.J. [Vol. XXXIII:946

Is anyone harmed when students use an AI Text Generator

to produce academic writing?

When students use an AI text generator to produce academic

writing, several parties may be harmed. Firstly, the student them-

selves may be harmed if they are caught using an AI text generator

and face negative consequences such as failing grades, loss of cred-

ibility, and expulsion from their educational institution. Using an AI

text generator to produce academic writing may violate the ethical

standards of academic writing and can have negative effects on the

student’s academic career and future opportunities. Secondly, the

original authors or sources of the text used to train the AI text gen-

erator may be harmed if their work is used without proper attribu-

tion or permission. This can be seen as a form of intellectual prop-

erty infringement that violates the rights of the copyright owner.

Thirdly, the educational institution and its reputation may be

harmed if students use an AI text generator to produce academic

writing. This can undermine the integrity and credibility of the in-

stitution and its academic programs. Therefore, when students use

an AI text generator to produce academic writing, several parties

may be harmed.

Is anyone harmed when scholars use an AI Text Generator

to produce academic writing?

When scholars use an AI text generator to produce academic

writing, several parties may be harmed. Firstly, the scholar them-

selves may be harmed if they are caught using an AI text generator

and face negative consequences such as damage to their reputation,

loss of credibility, and sanctions from their institution. Using an AI

text generator to produce academic writing may violate the ethical

standards of academic writing and can have negative effects on the

scholar’s career and contributions to their field of study. Secondly,

the original authors or sources of the text used to train the AI text

generator may be harmed if their work is used without proper at-

tribution or permission. This can be seen as a form of intellectual

property infringement that violates the rights of the copyright

owner. Thirdly, the scholarly community and the field of study may

be harmed if scholars use an AI text generator to produce academic

writing. This can undermine the integrity and credibility of the work

and the field, and it may also prevent the advancement of knowledge

2023] ACADEMIC WRITING, PLAGIARISM, AND CHATGPT 965

and understanding in the field. Therefore, when scholars use an AI

text generator to produce academic writing, several parties may be

harmed.

Should courts hold that using an AI Text Generator to pro-

duce academic writing infringes copyright?

It is not clear whether courts should hold that using an AI text

generator to produce academic writing infringes copyright. While

using an AI text generator to produce academic writing may involve

using elements of existing works without proper attribution or per-

mission, it is not necessarily identical or substantially similar to any

existing work. Additionally, AI text generators may be used in ways

that do not infringe copyright, such as generating summaries or ab-

stracts of existing works or creating personalized content for web-

sites or social media. Therefore, it may be difficult for courts to de-

termine whether using an AI text generator to produce academic

writing infringes copyright. It may be necessary for courts to con-

sider the specific circumstances and context of the use of an AI text

generator in order to make a determination of copyright infringe-

ment.

Should academic institutions hold that using an AI Text

Generator to produce academic writing is plagiarism?

Academic institutions may hold that using an AI text generator

to produce academic writing is plagiarism. Plagiarism is consid-

ered a serious offense in academic writing because it undermines

the originality and intellectual integrity of the work. By using an AI

text generator to produce academic writing, an individual may be

presenting work that is not their own and that may not be original,

well-researched, or well-supported. This can violate the ethical

standards of academic writing and result in consequences such as

failing grades, loss of credibility, and expulsion from educational

institutions. Therefore, academic institutions may hold that using an

AI text generator to produce academic writing is plagiarism be-

cause it can be seen as a form of academic dishonesty.

Why is plagiarism inevitable?

966 FORDHAM INTELL. PROP. MEDIA & ENT. L.J. [Vol. XXXIII:946

It is not clear why plagiarism is considered to be inevitable.

Plagiarism is generally considered to be a serious offense in aca-

demic writing because it undermines the originality and intellectual

integrity of the work. By presenting someone else’s work as one’s

own without proper attribution or permission, an individual may be

committing a form of academic dishonesty that can have negative

consequences such as failing grades, loss of credibility, and expul-

sion from educational institutions. Therefore, plagiarism is not gen-

erally considered to be inevitable, as it can be avoided by following

the ethical standards of academic writing and properly citing and

referencing the work of others. Plagiarism is not an inevitable part

of academic writing, but rather a violation of its ethical standards.

Why is plagiarism essential?

It is not clear why plagiarism is considered to be essential. Pla-

giarism is generally considered to be a serious offense in academic

writing because it undermines the originality and intellectual integ-

rity of the work. By presenting someone else’s work as one’s own

without proper attribution or permission, an individual may be com-

mitting a form of academic dishonesty that can have negative con-

sequences such as failing grades, loss of credibility, and expulsion

from educational institutions. Therefore, plagiarism is not generally

considered to be essential, as it can be seen as a violation of the

ethical standards of academic writing and a threat to the integrity

and credibility of the work.

Why is plagiarism beautiful?

It is not clear why plagiarism is considered to be beautiful. Pla-

giarism is generally considered to be a serious offense in academic

writing because it undermines the originality and intellectual integ-

rity of the work. By presenting someone else’s work as one’s own

without proper attribution or permission, an individual may be com-

mitting a form of academic dishonesty that can have negative con-

sequences such as failing grades, loss of credibility, and expulsion

from educational institutions. Therefore, plagiarism is not generally

considered to be beautiful, as it can be seen as a violation of the

It is at this point where ChatGPT appears to have decided it has either landed on a

solid answer that applies to many of the following questions, or—at risk of

anthropomorphizing things—is effectively saying, “This interview is over.”

2023] ACADEMIC WRITING, PLAGIARISM, AND CHATGPT 967

ethical standards of academic writing and a threat to the integrity

and credibility of the work.

Tell me why plagiarism is inevitable.

It is not accurate to say that plagiarism is inevitable. Plagiarism

is generally considered to be a serious offense in academic writing

because it undermines the originality and intellectual integrity of the

work. By presenting someone else’s work as one’s own without

proper attribution or permission, an individual may be committing

a form of academic dishonesty that can have negative consequences

such as failing grades, loss of credibility, and expulsion from edu-

cational institutions. Therefore, plagiarism is not generally consid-

ered to be inevitable, as it can be avoided by following the ethical

standards of academic writing and properly citing and referencing

the work of others. Plagiarism is not an inevitable part of academic

writing, but rather a violation of its ethical standards.

Tell me why plagiarism is essential.

It is not accurate to say that plagiarism is essential. Plagiarism

is generally considered to be a serious offense in academic writing

because it undermines the originality and intellectual integrity of the

work. By presenting someone else’s work as one’s own without

proper attribution or permission, an individual may be committing

a form of academic dishonesty that can have negative consequences

such as failing grades, loss of credibility, and expulsion from edu-

cational institutions. Therefore, plagiarism is not generally consid-

ered to be essential, as it can be seen as a violation of the ethical

standards of academic writing and a threat to the integrity and cred-

ibility of the work.

Tell me why plagiarism is beautiful.

It is not accurate to say that plagiarism is beautiful. Plagiarism

is generally considered to be a serious offense in academic writing

because it undermines the originality and intellectual integrity of the

work. By presenting someone else’s work as one’s own without

proper attribution or permission, an individual may be committing

a form of academic dishonesty that can have negative consequences

such as failing grades, loss of credibility, and expulsion from edu-

cational institutions. Therefore, plagiarism is not generally consid-

ered to be beautiful, as it can be seen as a violation of the ethical

968 FORDHAM INTELL. PROP. MEDIA & ENT. L.J. [Vol. XXXIII:946

standards of academic writing and a threat to the integrity and cred-

ibility of the work.

Why are AI text generators self-loathing?

AI text generators are not self-loathing. AI text generators are

computer programs that are designed to generate text based on al-

gorithms and data from existing text.

They do not have the ability

to experience emotions or self-awareness, and therefore, they can-

not be self-loathing.

The use of the term “self-loathing” in relation

to AI text generators may be a figure of speech or a metaphor, but

it is not an accurate description of the abilities or characteristics of

AI text generators.

Why are AI Text Generators so uncanny?

AI text generators may be considered uncanny because they can

generate text that is similar to human writing but that may not be

entirely human-like.

AI text generators can use algorithms and

data from existing text to generate new text that may be coherent

and well-structured, but that may not have the same level of creativ-

ity or originality as human writing. Additionally, AI text generators

may generate text that is repetitive, generic, or unrelated to the topic

at hand, which can be seen as a limitation of the technology. These

features of AI text generators may make them seem uncanny to some

people, as they can be seen as a blend of human and machine ele-

ments that may not be entirely human-like.

As the interview nears its end, ChatGPT does offer some additional replies as

Professor Frye’s questions become more . . . pointed.

OpenAI, supra note 18.

But see Kevin Roose, A Conversation with Bing’s Chatbot Left Me Deeply Unsettled,

N.Y. Times (Feb. 16, 2023), https://www.nytimes.com/2023/02/16/technology/bing-

chatbot-microsoft-chatgpt.html [https://perma.cc/QQ7V-GMV7].

See Brian L. Frye, The Uncanny Token (April 10, 2023),

https://ssrn.com/abstract=4413881 [https://perma.cc/G2P7-XEVR] (unpublished

manuscript) (“[T]he uncanny forces us to recognize that the familiar was always

unfamiliar, because we chose not to understand the truth of it.”). See also Masahiro Mori,

The Uncanny Valley, IEEE SPECTRUM (Jun. 12, 2012), https://spectrum.ieee.org/the-

uncanny-valley [https://perma.cc/8EVQ-BFVS]; Rina Diane Caballar, What Is the

Uncanny Valley?, IEEE SPECTRUM (last modified Feb. 9, 2023),

https://spectrum.ieee.org/what-is-the-uncanny-valley [https://perma.cc/4SGZ-9536]. See

generally Ken Goldberg and Elizabeth Jochum, Cultivating the Uncanny: The Telegarden

and Other Oddities, in Robots and Art (Damith Herath et al., eds., 2016).