LibKey Now Flags Both First and Second Order Retractions

Over the last decade, many in the scholarly research community have been sounding the alarm about journal article retractions being on the rise, for example:

Most prominent of these voices has been Dr. Ivan Oransky, co-founder of the Retraction Watch Database:

Thanks to an increase in awareness of this issue, new technologies have been developed to help alert library discovery tool users whenever they come across retracted items while searching. The thinking is that researchers should have the opportunity to closely examine retracted publications – and even publications that cite retracted papers but are not retracted themselves – as the research being reported within them may be compromised in some way.

One such tool, LibKey, that MSK community members can use via the library’s OneSearch catalog, flags retracted article citations whenever they appear in search result lists – see:

Starting in Summer 2025, LibKey expanded its retraction notification capabilities to also include “data about articles which cite one or more retracted articles”.

As per the LibKey (Third Iron) vendor’s newsletter:

“If a paper cites one or more retracted articles, LibKey will display an interstitial screen indicating which citations have been retracted”. 

For example – see:

If you have any questions or want additional guidance related to retractions, checkout “About Article Retractions” or feel free to Ask Us at the MSK Library.

Retractions, AI, and the Risks of Biomedical Misinformation

Retractions are a serious threat to biomedical research

In the high-stakes world of biomedical research, where published findings can shape clinical practice, policy decisions, and even drug approvals, the presence of retracted literature is not just an academic problem, it’s a public health concern. When flawed, fabricated, or irreproducible studies are left unchecked in the scientific ecosystem, they continue to misinform downstream research, meta-analyses, clinical guidelines, and ultimately, patient care.

Retractions aren’t rare, either. According to Retraction Watch, retractions have been steadily rising over the last decade. Still, many retracted studies continue to circulate in the literature without any obvious indication that they’ve been pulled. 

AI-powered biomedical searching and retractions

There are dozens, maybe even hundreds, of AI tools that promise to revolutionize biomedical literature searching. These tools claim to make life easier for clinicians and researchers by surfacing “the best” evidence quickly.

Unfortunately, these AI tools likely struggle with reliably flagging retracted articles. None of these tools appear to cross-reference the Retraction Watch Database, even though it’s one of the most comprehensive and up-to-date sources of retraction data.

The result? Users could end up citing, summarizing, or even basing treatment decisions on debunked science and the AI tools they trusted helped them do it.

Putting three AI search assistant tools to the test

To assess whether current AI-powered tools can reliably detect and communicate retracted biomedical research, we ran a small, but telling test using a recently retracted article:

Wu, S. Y., Sharma, S., Wu, K., Tyagi, A., Zhao, D., Deshpande, R. P., & Watabe, K. (2021). Tamoxifen suppresses brain metastasis of estrogen receptor-deficient breast cancer by skewing microglia polarization and enhancing their immune functions. Breast Cancer Research, 23, 1-16.

This article was retracted on May 12, 2025.

We located this article through the Retraction Watch Database, a critical resource for identifying retracted papers. We then tested how three popular AI tools responded when we searched for this article: 1) SciSpace, 2) Consensus, and 3) Elicit/

Baseline: Publisher and PubMed got it right

The article is clearly marked as retracted on both the publisher’s website (BMC, part of Springer Nature) and in PubMed. On BMC’s site, the article is branded with a bold red banner indicating that it has been retracted, and it links directly to the retraction notice.

In PubMed, the article’s retraction status is labelled. There’s a large red “Retracted Article” warning at the top of the article record. 

With Third Iron’s LibKey Nomad browser extension installed, the retraction warning also appeared directly in the search results list, providing an extra layer of protection.

These platforms demonstrate that it is possible to handle retractions clearly and transparently. But what happens when you try to search with an AI-powered tool?

1) SciSpace: No retraction flag, no awareness

SciSpace has gained traction for its AI-enabled “Papers” database and its Chat AI for article summarization. We searched for the retracted article using the Papers function. The article was retrieved with no indication that it had been retracted.

The PDF version offered by SciSpace appeared to be the original, unretracted version of the paper — there was no watermark or retraction notice. This likely occurred because SciSpace stored an earlier version of the file and does not dynamically update with retraction metadata or new PDFs.

When we asked the SciSpace Chat if the article had been retracted, the reply was: “Sorry, this is not discussed in the paper.” In other words, the AI agent only read the text of the article and had no external awareness of its retraction status.

SciSpace also failed to locate or return the associated Retraction Note (PMID: 40355962), which was published in the same journal.

2) Consensus: Accurate link, but no warning

Consensus is designed to help users quickly identify answers to scientific questions by ranking statements from published articles.

The article was returned in a basic search, and no indication of its retracted status was provided. The PDF link routed to the publisher’s version, which is good practice. Since BMC properly flags retractions, users landing on that page would see the retraction banner and be able to access the Retraction Note. While Consensus did not flag the article as retracted in its own search interface or metadata, it did link out to a source that did.

3) Elicit: Somewhat better!

Elicit offers two formats for reviewing articles: a plain-text view and a PDF view. When we searched for the retracted article via Elicit’s “Find Papers” tool, the results were mixed.

The article summary did not indicate that the paper had been retracted. The plain text view contained the word “RETRACTED” throughout the body text. Elicit also linked to a newer version of the article PDF that had the retraction stamp clearly watermarked across every page.

Lessons learned: We need accountability and standards

Users skimming article summaries, relying on search results, or using data extraction tables generated by AI tools might still miss the retraction unless they click deeper into the article itself. This is especially concerning in evidence synthesis workflows, where tools like Elicit auto-populate summary tables with study characteristics and conclusions—often without indicating the article has been retracted.

If AI is going to play a meaningful role in evidence retrieval and synthesis, it needs to be held to a higher standard. At a minimum, AI tools used in biomedical contexts must:

  • Flag retracted articles clearly and automatically
  • Cross-reference multiple retraction sources, including Retraction Watch
  • Date-stamp and cite their information sources transparently
  • Allow users to report errors or omissions easily

Until the current AI tools ecosystem improves, here are some tips to protect yourself and your team:

  • Always cross-check critical articles in the Retraction Watch Database or in PubMed
  • Use reference managers (like Zotero or EndNote) that integrate with PubMed and allow for manual annotations of retracted status
  • Avoid relying solely on AI summaries or ranking algorithms, especially for high-stakes research

It’s also worth noting that all the tools we tested (SciSpace, Consensus, and Elicit) are paid products and are effectively marketed as intelligent research assistants. Yet their inconsistent handling of retracted literature highlights the need for human-level vetting and cross-referencing.

In practice, this can take significantly more time than a traditional search if you’re trying to be thorough. Instead of accelerating research, these tools often introduce a false sense of efficiency, making it easy to miss red flags that would be obvious in a well-curated, librarian-led search process. The MSK Library team can help you navigate retraction risks, validate sources, and choose the right tools for your research. Connect with us today

 

Retracted Article Alerts Incorporated into LibKey Products, Including ONESEARCH

According to the co-founder of the Retraction Watch Database, Ivan Oransky, “Retraction Watch has witnessed a retraction boom since its founding 12 years ago”. This rise in retracted articles has translated into an increased risk of scholarly authors inadvertently citing a retracted paper without realizing it.

To mitigate this risk, a variety of library tools have started incorporating functionality that notifies their users whenever they come across an article that has been signposted as a retraction. To keep things as seamless as possible, these tools are not requiring their users to pause their research and jump to a second library product to look something up, but rather are incorporating these retraction flags/alerts as a safety “speed bump” in their process.

For example, Third Iron’s LibKey products like the MSK Library’s ONESEARCH discovery tool has begun including retraction status flags and reasons to help searchers make better informed decisions just as they are about to access the full-text PDF format of articles.

Here’s what it look like in practice – take, for example, this PubMed-indexed retracted article:

Hassan M, Watari H, AbuAlmaaty A, Ohba Y, Sakuragi N. Apoptosis and molecular targeting therapy in cancer. Biomed Res Int. 2014;2014:150845. doi: 10.1155/2014/150845. Epub 2014 Jun 12. Retraction in: Biomed Res Int. 2020 Aug 28;2020:2451249. PMID: 25013758; PMCID: PMC4075070.

The database citation record gets similarly flagged as a Retracted Article in ONESEARCH:

However, the retracted status becomes most obvious to the user at the critical point when they are about to decide whether or not they should invest time reading the full-text article:

Learn more About Article Retractions in Third Iron products or Ask Us at the MSK Library.