As I remarked: one of the issues for the “authors” is that they’re probably non-native English speakers, which is why I’m guessing they were using chatGPT for help in the first place. They could have totally legit results and used it to help them write the paper, so they didn’t know to look for or remove the offending phrase.
HOWEVER
the journal supposedly has editors/peer reviewers, right?
Heck, looking at it more closely, these may be their actual results and they may have used chatGPT just to generate some LaTeX code to make a table for them. I looked at some of the other search results, and that may have been similar issues – this is still on the editors.
“Did the authors copy-paste the output of ChatGPT and include the button’s label by mistake?” wondered Guillaume Cabanac, a professor of computer science at the University of Toulouse, in France, in a comment on PubPeer.
And, he added, “How come this meaningless wording survived proofreading by the coauthors, editors, referees, copy editors, and typesetters?”
…
“Regenerate response” is not the only sign of undeclared chatbot involvement Cabanac has seen. An even more egregious example is the phrase “As an AI language model, I …,” which he has found in nine papers until now.
Cabanac worries about how such flagrant sloppiness, arguably the tip of the iceberg, can slip past editorial staff and peer reviewers alike.
I mean, we are talking about an Elsevier journal, so despite the price maybe not.
Edit for the non-academics: Elsevier publishes maybe 25-50 of the top scientific journals in the world, so every university library has to subscribe to them. But they won’t sell you just those journals, and instead want to sell a big package of about 500 journals, most of which are absolute crap but cost a ton of money. I might be distorting the signal / noise ratio slightly, but it’s really bad.
My favorite anecdote (from another article) was a leading scientist being approached by someone tracking a citation, and being like, “uh, I know it says my name and all, but that paper doesn’t exist.”
How ChatGPT and other AI tools could disrupt scientific publishing
A world of AI-assisted writing and reviewing might transform the nature of the scientific paper.
Equity and inequity
When Nature surveyed researchers on what they thought the biggest benefits of generative AI might be for science, the most popular answer was that it would help researchers who do not have English as their first language (see ‘Impacts of generative AI’ and Nature621, 672–675; 2023). “The use of AI tools could improve equity in science,” says Tatsuya Amano, a conservation scientist at the University of Queensland in Brisbane, Australia. Amano and his colleagues surveyed more than 900 environmental scientists who had authored at least one paper in English. Among early-career researchers, non-native English speakers said their papers were rejected owing to writing issues more than twice as often as native English speakers did, who also spent less time writing their submissions2. ChatGPT and similar tools could be a “huge help” for these researchers, says Amano.
Certainly, here is a possible introduction for your topic:Lithium-metal batteries are promising candidates for high-energy-density rechargeable batteries due to their low electrode potentials and high theoretical capacities [1], [2]. However, during the cycle, dendrites forming on the lithium metal anode can cause a short circuit, which can affect the safety and life of the battery [3], [4], [5], [6], [7], [8], [9]. Therefore, researchers are indeed focusing on various aspects such as negative electrode structure [10], electrolyte additives [11], [12], SEI film construction [13], [14], and collector modification [15] to inhibit the formation of lithium dendrites. However, using a separator with high mechanical strength and chemical stability is another promising approach to prevent dendrites from infiltrating the cathode. By incorporating a separator with high mechanical strength, it can act as a physical barrier to impede the growth of dendrites. This barrier can withstand the mechanical stress exerted by the dendrites during battery operation, preventing them from reaching the cathode and causing short circuits or other safety issues. Moreover, chemical stability of the separator is equally important as it ensures that the separator remains intact and does not react or degrade in the presence of the electrolyte or other battery components. A chemically stable separator helps to prevent the formation of reactive species that can further promote dendrite growth. Researchers are actively exploring different materials and designs for separators to enhance their mechanical strength and chemical stability. These efforts aim to create separators that can effectively block dendrite formation, thereby improving the safety and performance of lithium-ion batteries. While there are several research directions to address the issue of dendrite formation, using a separator with high mechanical strength and chemical stability is an important approach to prevent dendrites from infiltrating the cathode and ensure safe operation of lithium metal batteries.
I skimmed the rest of the article and didn’t see any other obvious chat GPT artifacts, but that one was blatant. One does wonder if anybody edits (or even reads) the papers
