'ZDNET Recommends': What exactly does it mean?
ZDNET's recommendations are based on many hours of testing, research, and comparison shopping. We gather data from the best available sources, including vendor and retailer listings as well as other relevant and independent reviews sites. And we pore over customer reviews to find out what matters to real people who already own and use the products and services we’re assessing.
When you click through from our site to a retailer and buy a product or service, we may earn affiliate commissions. This helps support our work, but does not affect what we cover or how, and it does not affect the price you pay. Neither ZDNET nor the author are compensated for these independent reviews. Indeed, we follow strict guidelines that ensure our editorial content is never influenced by advertisers.
ZDNET's editorial team writes on behalf of you, our reader. Our goal is to deliver the most accurate information and the most knowledgeable advice possible in order to help you make smarter buying decisions on tech gear and a wide array of products and services. Our editors thoroughly review and fact-check every article to ensure that our content meets the highest standards. If we have made an error or published misleading information, we will correct or clarify the article. If you see inaccuracies in our content, please report the mistake via this form.
One of the biggest complaints about ChatGPT is that it provides information, but the veracity and accuracy of that information is uncertain. That's because ChatGPT doesn't provide sources, footnotes, or links to where it derived information used in its answers.
Also: How does ChatGPT work?
But that's not fully true.
If you know how to properly prompt ChatGPT, it will give you sources. Here's how.
To start, you need to ask ChatGPT something that needs sources or citations. I've found it's better to ask a question with a longer answer so there's more "meat" for ChatGPT to chew on.
Also: The best AI chatbots: ChatGPT and other interesting alternatives to try
Keep in mind that ChatGPT can't provide any information after 2021 and requests about information pre-internet (say, for a paper on Ronald Reagan's presidency) will have far fewer available sources.
Here's an example of a prompt I wrote on a topic I worked on a lot when I was in grad school:
Describe the learning theories of cognitivism, behaviorism, and constructivism
This is where a bit of prompt engineering comes in. A good starting point is with this query:
Please provide sources for the previous answer
I've found that this often provides offline sources, books, papers, etc. The problem with offline sources is you can't check their veracity. But it's a starting point. A better query is this:
Please provide URL sources
This specifically tells ChatGPT that you want clickable links to sources. You can also tweak this up by asking for a specific quantity of sources, although your mileage may vary in terms of how many you get back:
Please provide 10 URL sources
In our next step, we'll see what we can do with these.
Keep in mind this golden rule about ChatGPT-provided sources: ChatGPT is more often wrong than right.
Across the many times I've asked ChatGPT for URL sources, roughly half are just plain bad links. Another 25% or more are links that go to topics completely or somewhat unrelated to the one you're trying to source.
Also: How to use ChatGPT: Everything you need to know
For example, I asked for sources on a backgrounder for the phrase "trust but verify," generally attributed to 1980s US President Ronald Reagan. I got a lot of sources back, but most didn't actually exist. I got some back that correctly took me to active pages on the Reagan Presidential Library site, but where the page topic had nothing to do with the phrase in question.
I had a bit better luck with my learning theory question from step 1. There, I got back offline texts from the people who I knew from my studies had actually worked on those theories. I also got back URLs, but again, only about two in ten actually worked or were accurate.
Also: ChatGPT fraud is on the rise: Here's what to watch out for
But don't despair. The idea isn't to expect ChatGPT to provide sources that you can immediately use. If you instead think of ChatGPT as a research assistant, it will give you some great starting places. Use the names of the articles (which may be completely fake or just not accessible) and drop them into Google. That will give you some interesting search queries, which will more than likely lead to some interesting reads and material that can legitimately go into your research.
One final point: if you merely cut and paste ChatGPT sources into whatever research you're doing, you're likely to get stung. Use it for clues, not for a way to avoid the real work of research.
APA style is a citation style that's often required in academic programs. APA stands for American Psychological Association, and I've often thought that they invented these style rules in order to get more customers. But, seriously, the definitive starting point for APA style is the Perdue OWL. It provides a wide range of style guidelines. Be careful: online style formatters may not do a complete job and you may get your work returned by your professor. It pays to do the work yourself, and use care doing it.
This is a good question. I have found that sometimes -- sometimes -- if you ask ChatGPT to give you more sources, or re-ask for sources, it will give you new listings. If you tell ChatGPT that the sources it provided were erroneous, it will sometimes give you better ones. It may also just apologize and give excuses. Another approach is to re-ask your original question with a different focus or direction, and then ask for sources for the new answer.
Also: 5 ways you can use ChatGPT to help you write essays
Once again, my best advice is to avoid treating ChatGPT as a tool that writes for you and more as a writing assistant. Asking for sources so you can just cut and paste a ChatGPT response is pretty much plagiarism. But using ChatGPT's response and any sources you can tease out of it as clues for further research and writing is a completely legitimate way to use this intriguing new tool.
For some links, it's just link rot. Since all sources are at least three years old, some links may have changed. Other sources are of indeterminate age. Since we don't have a full listing of all of ChatGPT's sources, it's impossible to tell how valid they were to begin with. But since ChatGPT was trained mostly without human supervision, we know that most of its sources weren't vetted, and so could be wrong, made-up, or completely non-existent.
Trust, but verify.
You can follow my day-to-day project updates on social media. Be sure to follow me on Twitter at @DavidGewirtz, on Facebook at Facebook.com/DavidGewirtz, on Instagram at Instagram.com/DavidGewirtz, and on YouTube at YouTube.com/DavidGewirtzTV.