Using ChatGPT without citation could be seen as unethical or even regarded as plagiarism. It\u2019s a debate that has been raging in academic, legal, journalistic and other professional circles.\u00a0<\/p>\n
But there are other, perhaps more timely and important, questions: Question No. 1: Does ChatGPT itself plagiarize other people\u2019s work? Question No. 2: And does it engage in copyright infringement?<\/p>\n
Lawyers, and AI experts have their own view, but how would ChatGPT answer these questions? MarketWatch decided to find out.<\/p>\n
First, some background: The question of whether ChatGPT itself engages in copyright infringement is the subject of several class-action lawsuits on behalf of several authors, including the comedienne Sarah Silverman.\u00a0<\/p>\n
Silverman last month announced that she had decided to join a class-action suit against OpenAI and Facebook-owner Meta ChatGPT, an artificial-intelligence search engine, is a product of OpenAI, and made its free, public debut last December. It can answer questions, give advice, produce creative writing, research academic and legal issues \u2014 with varying degrees of accuracy \u2014 and some observers even say it can even be employed by financial advisers to pick stocks.<\/p>\n OpenAI\u2019s algorithm sweeps across the web for answers to dish out in seconds to its users, using large language models (or LLMs), a kind of artificial intelligence that mimics human responses.<\/p>\n Joseph Saveri and Matthew Butterick, the lawyers representing Silverman and other writers, were blunt in their view of OpenAI and other AI chatbots, and are attempting to draw a direct line between aggregation of information from the web, plagiarism and copyright infringement. In a joint statement, they wrote that OpenAI and Meta are \u201cindus\u00adtrial-strength pla\u00adgia\u00adrists that vio\u00adlate the rights of book authors.\u201d\u00a0<\/p>\n \u201cMuch of the mate\u00adr\u00adial in the train\u00ading datasets used by OpenAI and Meta comes from copy\u00adrighted works \u2014 includ\u00ading books writ\u00adten by plain\u00adtiffs \u2014 that were copied by OpenAI and Meta with\u00adout con\u00adsent, with\u00adout credit, and with\u00adout com\u00adpen\u00adsa\u00adtion,\u201d the lawyers said in a statement. \u201cMany of these books likely came from \u2018shadow libraries,\u2019 web\u00adsites that dis\u00adtrib\u00adute thou\u00adsands of pirated books and pub\u00adli\u00adca\u00adtions.\u201d (Saveri and Butterick did not respond to a request for comment.)<\/p>\n Tim Giordano, a partner at the Clarkson Law Firm, has also filed class-action suits against both OpenAI and Google parent Alphabet Inc. GOOG, Halimah DeLaine Prado, Google General Counsel, said in a statement to MarketWatch: \u201cWe\u2019ve been clear for years that we use data from public sources \u2014 like information published to the open web and public datasets \u2013 to train the AI models behind services like Google Translate, responsibly and in line with our AI Principles. American law supports using public information to create new beneficial uses, and we look forward to refuting these baseless claims.\u201d\u00a0<\/p>\n Last month, the U.S. Federal Trade Commission opened an investigation into whether ChatGPT maker OpenAI engaged in unfair or deceptive practices that caused \u201creputational harm\u201d to consumers.<\/p>\n The FTC asked OpenAI to detail steps they have taken to address or mitigate the risks to prevent generating information about \u201creal individuals that are false, misleading or disparaging,\u201d according to a 20-page letter.<\/p>\n (OpenAI did not respond to multiple requests for comment.)<\/p>\n There is an important legal difference between copyright infringement and plagiarism. \u201cCopyright infringement includes the unauthorized or unlicensed copying of a work subject to copyright,\u201d according to the University of Illinois Chicago.\u00a0<\/p>\n \u201cPlagiarism is using someone else\u2019s work or ideas without giving proper credit,\u201d it adds. \u201cIn other words, because you are not giving attribution to the owner of the original work or idea \u2014\u00a0 you are presenting the idea or thought as your own.\u201d<\/p>\n Question No. 1. This reporter asked ChatGPT: \u201cDoes ChatGPT engage in copyright infringement?\u201d\u00a0<\/p>\n The response was definitive, but comes with multiple qualifications.<\/p>\n \u201cNo, ChatGPT does not engage in copyright infringement,\u201d ChatGPT responded. \u201cIt generates text based on the input it receives and the training data it has been provided, but it does not intentionally replicate specific copyrighted content.\u201d<\/p>\n And now for the caveat:<\/p>\n \u201cHowever, it\u2019s important to note that the text it generates can sometimes resemble existing content, and there is a possibility that generated text could inadvertently resemble copyrighted material,\u201d it adds. \u201cUsers should be cautious and responsible when using the model to avoid any potential copyright issues.\u201d<\/p>\n The issue of whether ChatGPT engages in copyright infringement appears to hinge on the word \u201cresembling\u201d \u2014 rather than outright \u201ccopying\u201d \u2014 somebody else\u2019s work, observers say. Whether a court would agree with that distinction, and conclude that OpenAI\u2019s aggregation of other people\u2019s work on the web did not rise to the level of copyright infringement, remains to be seen.<\/p>\n \u201cIn terms of ChatGPT\u2019s response to your prompt, it\u2019s a good example of what we often see from ChatGPT \u2014 authoritative-sounding but substantively flawed statements,\u201d said Dave Fagundes, a professor at the University of Houston Law Center who writes and teaches about copyright.\u00a0<\/p>\n \u201cFirst, the response assumes that the only possible form of infringement is in the possible creation of infringing output \u2014 that is, content that is identical to or substantially similar to copyrighted works of authorship \u2014 when in fact the major claim averred on this relates to the LLMs\u2019 \u201clearning\u201d process,\u201d he said. \u201cSecond, the response assumes that copyright infringement needs to be intentional, when that is not an element under U.S. law.\u201d<\/p>\n The allegation that ChatGPT and others engage in copyright infringement has little or nothing to do with the result of prompts, he said, and more and\/or everything to do with the process by which these machines learn. \u201cThe latter entails creating verbatim reproductions of billions of works culled from the internet without authorization from their owners,\u201d Fagundes told MarketWatch. \u201cThe plaintiffs in the lawsuits you mentioned are primarily arguing that it is this process that amounts to infringement.\u201d<\/p>\n \u201cIn copyright law, there is basically no such thing as innocent or accidental infringement, and to the extent there is, ChatGPT cannot avail itself of that defense,\u201d added Christopher Buccafusco, a professor at Duke University School of Law, whose research covers a range of topics, including intellectual property law. \u201cChatGPT and other generative AI models are trained on huge amounts of data, and that data is technically copied according to copyright law.\u201d<\/p>\n \u201cImportantly, though, in copyright law, not all copying is copyright infringement,\u201d he told MarketWatch. \u201cGenerative AI models engage in non-expressive copying \u2014 they are copying not to repeat what they copy but to learn from what they copy. And according to most scholars, this sort of non-expressive copying should be treated as non-infringing fair use.\u201d<\/p>\n Fangundes agrees. Plaintiffs\u2019 arguments that the technology used by AI infringe their copyrights through their learning processes may well founder on a \u201cfair use\u201d theory, he said. \u201cCourts have repeatedly held that non-expressive uses of copyrighted works by copy-reliant technologies don\u2019t infringe \u2014 even in the absence of permission to use the copied works because they are statutorily protected fair uses of those works,\u201d he said. \u201cThis is, for example, why Google Books\u2019 copying millions of volumes without authorization to populate its database was held not infringing.\u201d<\/p>\n And so to Question No. 2. This reporter asked ChatGPT: \u201cIs ChatGPT plagiarism?\u201d\u00a0<\/p>\n Here is the chatbot\u2019s response: \u201cAs an AI language model, I am a tool developed by OpenAI to generate human-like text based on patterns in the data I was trained on. While I don\u2019t have the capability to intentionally plagiarize, I can generate responses that may resemble information found elsewhere on the internet.\u201d<\/p>\n That\u2019s not a yes, and that\u2019s not a no. Either way, ChatGPT also acknowledges that its answers may contain plagiarized material.<\/p>\n ChatGPT added: \u201cIt\u2019s important to note that if a user submits a question or prompt that contains copyrighted material or is an exact copy of someone else\u2019s work without proper attribution, generating a response based on that content could potentially be considered plagiarism. However, OpenAI encourages users not to use the AI for unethical purposes, including plagiarism.\u201d<\/p>\n \u201cIf you use information or text generated by ChatGPT, it\u2019s essential to properly attribute it if required and ensure that you comply with copyright laws and ethical guidelines,\u201d ChatGPT\u2019s answer concluded. \u201cUsing the AI responsibly and ethically is crucial to maintaining a positive impact on the community and avoiding potential legal issues.\u201d<\/p>\n So ChatGPT says it is aware that its actions can lead to plagiarism. That appears to put the responsibility at the feet of the user, observers say. For all its sophistication and speed, nowhere does ChatGPT say it provides citations.<\/p>\n \u201cIt\u2019s basically saying it\u2019s the user\u2019s responsibility to check up on AI. It moves the responsibility away from itself,\u201d said Lisa McLendon, a professor of journalism and mass communications at the University of Kansas. \u201cIt\u2019s not going to come out and say, \u2018Students use me to cheat.\u2019\u201d\u00a0<\/p>\n \u201cThe bigger issue is that people trust it too much,\u201d she added,\u201dand it\u2019s not reliable.\u201d<\/p>\n The issue is fraught, but far from cut-and-dry. \u201cBy and large, leveling plagiarism charges toward generative AI is not as easy as it might seem,\u201d Dr. Lance Eliot, a global AI expert, told MarketWatch.<\/p>\n \u201cEven if the generative AI perchance emits word-for-word some other existing content, you can simply ask the generative AI what the source was,\u201d he said. \u201cIt would certainly be better for generative AI to always provide a designated citation, though this is not necessarily how generative AI has been devised. A follow-up prompt to the generative AI might get you the source name, and thus you have essentially resolved the alleged plagiarism, albeit by your own overt efforts.\u201d<\/p>\n However, it may not be that simple. Elliot said AI might not have stored the cited source, may have incorrectly cited a source, or even made up a cited source, \u201csometimes referred to as an AI hallucination, an absurd and disfavored anthropomorphic phrase that regrettably has garnered popular appeal.\u201d Another possibility is that the generative AI will indicate a wrong source that had nothing to do with the emitted content.<\/p>\n \u201cAll in all, the best bet is to do an online lookup via an Internet search engine to potentially ferret out the source yourself,\u201d he said. \u201cThis is a bit daunting since you might not have realized that some essay or portion of an essay does contain plagiarized material.\u201d<\/p>\n \u201cSorry to say, that\u2019s the risks you take using today\u2019s generative AI,\u201d Elliot added.<\/p>\n The issue of allegedly misappropriating people\u2019s work, intentionally or not, is not going away. More than 4,000 writers \u2014 including Margaret Atwood, Louise Erdrich and Jodi Picoult \u2014 signed a letter in late June to the CEOs of OpenAI, Google, Microsoft (Microsoft, a financial backer of OpenAI, declined to comment.)<\/p>\n On a practical level, how can you check sources when ChatGPT does not give any links, like Google Search, or citations, like Wikipedia, the free online encyclopedia edited and written by millions of volunteers around the world. \u201cIt\u2019s compiling information. It\u2019s like Wikipedia,\u201d said Aaron Chimbel, dean of the Jandoli School of Communication at St. Bonaventure University in New York. \u201cIt\u2019s a major technological interruption.\u201d<\/p>\n He put ChatGPT on par with Wikipedia. \u201cNobody in academia or journalism would use Wikipedia as a source as it compiles information from different sources,\u201d Chimbel told MarketWatch. \u201cYou might use it as a starting point rather than an official source.\u201d<\/p>\n \u201cWikipedia has the Wiki editors, although there have been many instances of errors,\u201d he added. \u201cWith any new technology, it takes a while to work through the process of the quality and how we use it, whether it\u2019s journalism, education or the law. It applies to anybody who writes things. It\u2019s going to apply to really every field.\u201d<\/p>\n \u201cIt\u2019s one of these things that will change how we work across all fields,\u201d he told MarketWatch. \u201cIt\u2019s a huge concern in higher education, journalism and in lots of fields. At the same time, it\u2019s not going away.\u201d<\/p>\n If you want to use AI ethically, tread very carefully. \u201cLike a box of chocolates, you never know what you might get out of generative AI,\u201d Elliot, the AI expert, said. \u201cIt is incumbent upon the user of generative AI to check and double-check any emitted essays. Those that merely do a grab-and-go are going to possibly find themselves in hot water and attempt to finger point back at the generative AI and the AI maker might do you little good.\u201d<\/p>\n He also warns of an ethical \u201cboomerang,\u201d and advises consumers to familiarize themselves with the policies of AI generators. \u201cThe AI maker can claim you didn\u2019t abide by the licensing requirements,\u201d he said, \u201cand furthermore, if any third party tries to go after the AI maker, you usually have also agreed via the licensing to indemnify the AI maker \u2014 meaning that you might be on the hook for any legal bills incurred by the AI maker when defending against a claim being made by an action you took to disseminate an emitted essay.\u201d<\/p>\n Some academics have argued that graduate students can leverage the power of AI for their initial research. That is, use it as a guiding light or sophisticated search engine rather than copying and pasting the information it aggregates.\u00a0<\/p>\n Doug Ward, associate professor at the School of Journalism and Mass Communications at Kansas University, recently authored an article entitled, \u201cWhy generative AI is now a must for graduate classes.\u201d In it, he suggests that AI could have a very beneficial effect on graduate education.\u00a0<\/p>\n \u201cThe question there, though, isn\u2019t how or whether to integrate AI into coursework,\u201d he wrote.\u201cRather, it\u2019s how quickly we can integrate AI into methods courses and help students learn to use AI in finding literature; identifying significant areas of potential research; merging, cleaning, analyzing, visualizing, and interpreting data; making connections among ideas; and teasing out significant findings. That will be especially critical in STEM fields and in any discipline that uses quantitative methods.\u201d<\/p>\n Ethan Mollick, a \u00a0professor at the Wharton School of the University of Pennsylvania, similarly wrote last month that ChatGPT with Code Interpreter \u201callows the AI to do math (very complex math) and do more accurate work with words (like actually counting words in a paragraph), since it can write Python code to address the natural weaknesses of large language models in math and language. And it is really good at using this tool appropriately.\u201d<\/p>\n St. Bonaventure University\u2019s Chimbel said one side of the argument surrounding AI says we need to ban any kind of ChatGPT for students and academics and in other professions, but others are exploring how we can incorporate it. \u201cA total ban may not be practical given how pervasive it is,\u201d he said. \u201cWe are looking at it as a course-by-course approach.\u201d<\/p>\n But that does not and should not undercut guidelines related to standards of misconduct, Chimbel said. \u201cSomebody who presents material as their own is still academic misconduct,\u201d he added. \u201cBut what if someone uses an AI program as a prompt to get them thinking? It\u2019s all in the nuance between the broad type of plagiarism vs. some of these other issues.\u201d<\/p>\n Programs to detect plagiarism and AI also need fine-tuning in terms of efficacy, observers say. Edward Tian, a senior at Princeton University, announced on social media in January<\/a> that he had created an app, GPTZero, to \u201cquickly and efficiently detect\u201d if a student or professional is using text originally written by ChatGPT. It seems to be an in-demand service: Thus far, his post has been viewed 7.8 million times.<\/p>\n So should the ordinary Joe Soap be concerned about AI potentially plagiarizing other people\u2019s work? \u201cKeep mumbling to yourself the famous catchphrase of caveat emptor,\u201d Elliot said. \u201cAs the user of generative AI services, look in the mirror to see who is supposed to be wary. Whether AI makers can stand up to potential ethical outrage over allowing plagiarism to occur by their generative AI is yet to be seen. Meanwhile, keep your eyes wide open and remain ever vigilant to double-check and triple-check anything that generative AI emits.\u201d<\/p>\n So can ChatGPT be trusted \u2014 and can it be trusted to answer prompts about the nature of its own services as they relate to plagiarism and copyright infringement? Chimbel has his doubts. AI chatbots can spit out information that may not be vetted, accurate or clear, he said. \u201cIt does that when you ask tricky questions.\u201d<\/p>\n<\/p><\/div>\n
\n META,
\n
\n for copyright infringement. The lawsuit contends that her 2010 memoir was copied by the AI system \u201cwithout consent, without credit and without compensation.\u201d\u00a0<\/p>\n
\n GOOGL,
\n
\n
\n The lawsuits allege that they have engaged in theft of personal information and copyright infringement, among other allegations. \u201c\u2018Publicly available\u2019 has never meant free to use for any purpose,\u201d Giordano said in a statement.<\/p>\nDoes ChatGPT engage in copyright infringement?<\/strong><\/h2>\n
What do lawyers think of this response?\u00a0<\/strong><\/h2>\n
Is ChatGPT plagiarism?<\/strong><\/h2>\n
So what are we to make of this response?<\/strong><\/h2>\n
\n MSFT,
\n
\n Meta and other AI developers, alleging that they exploit their work and \u201cmimic and regurgitate\u201d their language, style and ideas, the Associated Press reported.\u00a0<\/p>\nCan AI be used ethically?<\/strong><\/h2>\n