A Conference Board survey, in collaboration with Ragan Communications, found that while almost 90% of marketing and communication professionals have used generative AI (GenAI) tools, their feelings about the usefulness of these tools are mixed—only about four out of ten expect GenAI to improve work quality and creativity—three in ten expect it to deteriorate outputs.
So I decided to do some further research and experimenting on my own.
A Slippery Slope
There are some great potential uses for generative AI, or GenAI—tools like ChatGPT, Bard, Jasper, and others. But there’s peril as well. These tools have been found to “hallucinate”—basically make stuff up as some have found to their chagrin, and detriment.
Some New York lawyers, for instance, have been sanctioned for their use of ChatGPT—not the actual use of the tool, but their failure to fact check the content generated which included false citations. Others’ use of these tools, without appropriate due diligence, can result in impacts ranging from these extremes to minor embarrassment, depending on the purpose of their use.
What many are discovering to their chagrin is that generative AI tools commonly “hallucinate” or, in other words, “make stuff up.”
It’s happened to me.
I was looking for examples of companies with employee resource groups (ERGs) specifically focused on older demographics—Baby Boomers and beyond. It generated what appeared to be an impressive list but, since I know the tool I was using didn’t have content beyond 2021, I went to the companies’ websites to verify the groups were still in existence.
I couldn’t find any of them.
So I went back to the tool and asked: “Did you make these ERGs up?” Its response: “I apologize for the confusion caused earlier. The examples I provided in my previous response were hypothetical and not based on specific knowledge of existing ERGs.”
I asked it to generate another list and specifically said: “do not make these up; use real examples.” It gave me another impression list, but when I asked it again: “Did you make these up?,” I got the same response.
Troubling.
Unfortunately, the tool has misled me in other ways. One use case I thought would be helpful was to have the tool generate SEO-related content—titles, email subject lines, meta copy, etc.—for blog posts which need to be a certain word or character length. And I discovered that it didn’t always adhere to the length requirements, even when I asked it over and over again to do so.
Also troubling.
I’ve come up with some of my own ways of both minimizing these outputs through my prompts and doing some additional fact-checking, but wondered how others were tackling the issue. So I reached out to other content marketers and GenAI experts. Here’s what they had to say.
Why Does AI “Hallucinate”?
The trouble with GenAI say those most familiar with how it works, is that it tends to be a “people pleaser.” It really want to give you useful information.
“The problem is, when it doesn’t know somethi8ng, it pretends to know, instead of saying ‘I don’t have enough information’,” says Juliet Dreamhunter, a productivity and AI consultant with Juliety.
Dreamhunter once input a link to an article she’d written, asking ChatGPT to “please summarize this article for me.” It generated a one-paragraph summary. Dreamhunter knew the content well. She could tell immediately that it was “completely made up.”
After learning about the concept of hallucinations, she says, she went back asked how it had written the summary. From the “confession,” she says, “I found out that it didn’t follow the link but generated a summary of what an article like this could be about, based on the keywords in the URL and its own knowledge base.”
Despite the potential for hallucinations, there are steps that content marketers can take to minimize the potential for error—and check for it.
Enlist the Assistance of Domain Experts
Fawaz Naser is CEO of Softlist.io, a platform that compares tools and software to optimize productivity. He shares an experience his firm recently encountered when using AI to generate content for its marketing campaigns.
“While the created content was grammatically perfect and contextually relevant, it incorporated some facts about our company’s history that were unrealistic,” he says. “It claimed that we expanded into markets that we had not yet penetrated, probably extrapolating based on our rapid growth in our existing markets.”
His recommendation: “By leveraging AI as a tool, rather than a decision-maker, organizations can make AI’s strength work for them while also mitigating ‘hallucination’ risks.” He suggests:
- Using relevant domain experts to validate AI outputs.
- Continuous re-evaluation and retraining of the AI model with updated, accurate data.
- Validate AI output using multiple models.
- Remind stakeholders—internal or external—that AI is not infallible but a tool that needs to be controlled and supervised.
As with any other tool, it’s becoming increasingly clear that GenAI requires human oversight to ensure accuracy and relevance.
Use GenAI Appropriately
John Pennypacker, VP of Sales & Marketing at Deep Cognition, a company working with next-generation AI platforms and solutions, says his number one recommendation when using tools like ChatGPT is to never use them as an encyclopedia. ChatGPT, he says, is “great for organizing your content, tweaking here and there, or rewriting your content—but never depend on it for fact-checking.”
He shares an experience he had when generating content about Python programming. “I fed it the topic and some basic points, and it came up with a pretty comprehensive piece,” he says. But, he adds: “Upon fact-checking, I discovered that it had made up a Python function. It was an impressive, creative ‘hallucination,’ which wasn’t actually in the Python library!”
Pennypacker’s example illustrates how critical it is to check the output generated by GenAI tools, regardless of how impressive and credible that output may seem.
“Despite AI’s ability to generate content and provide suggestions, we are ultimately responsible for checking facts, ensuring accuracy, and imparting the right tone and flavor,” Pennypacker says.
Dan Chadney, a web designer, front-end developer, and blogger, says that the best way to avoid hallucinations is to “train” the AI before making a request. “Providing extra context and actual facts to the AI first will always yield the best results,” he says. “I often use a ChatGPT plugin that provides web browsing functionality. Then when writing my prompt I’ll ask the AI to look at specific URLs and use them as references for facts.”
Another tool Chadney recommends is Perplexity AI. “I’ve found this to be one of the most useful tools ever, because it also provides sources—and URLs—for each fact returned. I’ve used it for writing biographies, stats, and software reviews. It’s still best to always double-check your facts, but Perplexity cuts out so much of the legwork, it’s a huge time saver.”
Better Results Likely Over time
Kateryna Reshetilo, head of marketing at Greenice, a web development firm, says that her firm has noticed that accuracy increases with each new Large Language Model. For instance, she shares:
“We built an AI-powered chatbot for our website (you can see it in action https://greenice.net/) to answer visitors’ questions about our company and services. Initially, we used the GPT-3 model and trained it on our website content as well as a database of FAQs. However, this model was constantly hallucinating, making up information about our company and even providing URL links to pages that did not exist. We then switched to the GPT-3.5 model, and now we get correct answers most of the time. This model turned out to be much more suited for chatbots.”
For now, Reshetilo says, “generative AI is like a trainee or a new assistant. It requires a lot of human supervision and fact-checking.”
Despite the glitches, with appropriate oversight and the right applications, GenAI tools are definitely proving to offer opportunities for efficiencies that make continued experimentation definitely worth the effort.
(NOTE: This piece originally appeared in Information Today)
About Us
Strategic Communications, LLC, works with B2B clients to help them achieve their goals through effective content marketing and management with both internal and external audiences. We work with clients to plan, create and publish high-quality, unique content. Whether on- or offline, or both, we’ll help you achieve desired results at reasonable rates.
In addition to content creation we specialize in helping B2B clients raise awareness and drive website traffic through a strong LinkedIn and Twitter presence.
(Strategic Communications is certified as a Woman-Owned Business Enterprise through the Wisconsin Department of Administration.)
Stay up-to-date on the latest traditional and digital marketing trends and insights for communication leaders: subscribe to our monthly e-newsletter.
Tags: AI in content marketing, artificial intelligence, GenAI, GenAI for marketing, generative AI