Blog post with tips for spotting hallucinations in AI generated content

Image by Afif Ramdhasuma from Pixabay

A new post published December 16, 2025 on the blog, Card Catalog, discusses practical tips for identifying hallucinations in AI generated citations. The post, titled, How to spot AI hallucinations like a reference librarian by Hana Lee Goldin, provides a quick, plain-language overview of why AI has the tendency to hallucinate references, and some tell-tale signs of hallucinated content. 

Something I particularly appreciate is that, in addition to providing tips for determining if a citation exists, the post also provides tips for verifying whether the AI is accurately summarizing the sources it's citing, being a vital check that often gets overlooked in AI generated content.

Happy reading, and hope everyone has a great weekend! ⛄

Free NNLM Webinar: Hospital Librarians Going Virtual

Pay No Attention to That Librarian Behind the Curtain!

by Dora Davis, WHSLA Professional Development Chair

 

While doing my usual crawl of regional offerings (just call me the Nancy Drew of Professional Development), I stumbled upon a gem: Region 7 is hosting a webinar on “Hospital Librarians Going Virtual.”

 

Most of us have already made the leap into virtual spaces—hello juggling all the things with only your keyboard and mouse—but aren’t you curious to see how others have navigated this transition? From creative outreach strategies to tech hacks that actually work, I’m curious to hear what’s worked (and what we wish we had never attempted).

 

When I first transitioned to virtual services, it felt a little like the Wizard of Oz moment—“Pay no attention to that man behind the curtain!” Suddenly, all the behind-the-scenes magic we used to do in person had to happen online. The curtain was pulled back, and our patrons could see the gears turning live via Teams (or Zoom or Webex or….): the tech troubleshooting, the resource wrangling, the creative pivots, that time someone banged on my door and my camera fell off so all anyone could see was the dirty ceiling in my office. My first virtual education session was nerve-wracking—I worried no one would show up, and then 42 people logged in!  Talk about deer-in-the-headlights dodging oncoming traffic. But that was my aha moment: Going virtual wasn’t just a workaround; it was an opportunity to reach more people than ever before.

 

The best part? This webinar is free. No budget approvals, no expense reports—just pure professional development goodness at the click of a button.

 

If you’ve ever wondered:

• How do other hospital librarians keep that personal touch online?
• What tools are making their lives easier?
• Who’s figured out the secret to making virtual orientations actually fun?
• How many of us are sporting “the best pair of socks you’ve ever worn” behind that curtain?

 

Then this webinar might be worth your time.  Go ahead and take a peek because although there’s no place like home, sometimes a visit to someone else's home gives you that idea you didn’t know you needed.

 

Register here: Hospital Librarians Going Virtual

 

In the meantime, watch out for flying monkeys!

 

Dora 

Can automatic indexing algorithms compare apples to Apple's?: An overview of automatic indexing in PubMed, errors, and potential band aids.

 

Image by Michal Jarmoluk from Pixabay

Inane indexing

As librarians, we've encountered some…well, let's say interesting indexing choices in PubMed records.

Such as this case, where an article about Apple iPad Pro's was indexed with the MeSH term, "Malus" (being the genus name for apple tree)…

…or this case, where an article about early identification of autism was assigned the MeSH term, "humans." Anything else? Nope. Just "humans."

So what's going on here? Well, there are a few different ways a record can be indexed in PubMed [1]:

• Manual: This is where a record was indexed manually by an indexer at the National Library of Medicine (NLM).
• Automated: This is where a record was indexed by an algorithm, with no review by human indexers.
• Curated: This is where a record was indexed by an algorithm, but was later reviewed/modified by human indexers.

If the indexing of a record seems particularly bizarre, such as in our examples, odds are the record may have been automatically indexed.

A bit of Background on Automatic Indexing in PubMed

Automatic indexing isn't new to PubMed. In 2002, automatic indexing began as simple suggestions given to indexers at the NLM as they reviewed a record [2-6]. In 2011, first line automated indexing with human review was implemented for a selection of 14 journals [2, 4, 6, 7]. This progressed to full automatic indexing for all OLDMEDLINE records in 2015, comments and backlogged citations in 2016, and, finally, full automatic indexing for all MEDLINE journals in 2022, with the NLM's newest automatic indexing algorithm, Medical Text Indexer NeXt generation (MTIX) being introduced in 2024 [4, 7, 8].

While automatic indexing has improved efficiency, it has also resulted in issues relating to precision and recall, as demonstrated in the examples I had alluded to earlier. A few studies have documented these errors more formally [3, 9-12], including an article I recently published in the Journal of the Medical Library Association (JMLA), which examined precision errors observed in a sample of MEDLINE records automatically indexed with the MeSH term, Malus, being the genus name for apple tree [13].

How do I check how a PubMed record was indexed?

For those curious, there's a nifty trick you can use to check how an item is indexed. You can do this by looking at the PubMed record in XML. To access a PubMed record in XML, simply use the URL below, replacing the highlighted number with the PMID of the record you would like to check.

https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=24410017%2c11700088&retmode=xml

The indexing method is typically listed to the right of the label "indexingmethod=".

Below are screenshots of the XML of both of our examples from earlier. Sure enough, they were both automatically indexed.

Link to XML for Example 1

Link to XML for Example 2

What can we do about automatic indexing errors in PubMed?

While we can't fix automatic indexing errors in PubMed, ourselves, or wholly prevent them from occurring, there are a few ways to ameliorate their effects.

In addition to conducting additional studies on automatic indexing errors and reporting errors to the NLM HelpDesk, librarians can instruct researchers to use standardized language and the very MeSH terms they would like to see assigned to their records in the titles and abstracts of their manuscripts (at the least, this way, records may have correct MeSH terms appear alongside the erroneous ones).

Fellow librarians from the University of Iowa developed a checklist that has additional tips for helping researchers reduce the effects of automatic indexing errors in their own manuscripts [14].

Will automatic indexing algorithms ever compare, with 100% accuracy, apples to Apple's? Who knows. But, regardless of whether indexing errors cause you laughter or grief, they're likely to be sticking around for a while.

 

Works Cited / Fun Reading

1.      Incorporating values for indexing method in MEDLINE/PubMed XML [Internet]. NLM Technical Bulletin; 2018. Available from: https://www.nlm.nih.gov/pubs/techbull/ja18/ja18_indexing_method.html#note

2.      Mork J, Aronson A, Demner-Fushman D. 12 years on - Is the NLM medical text indexer still useful and relevant? J Biomed Semantics. 2017 Feb 23;8(1):8. Epub 20170223. DOI: 10.1186/s13326-017-0113-5. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5324252/pdf/13326_2017_Article_113.pdf.

3.      Chen E, Bullard J, Giustini D. Automated indexing using NLM's Medical Text Indexer (MTI) compared to human indexing in Medline: a pilot study. J Med Libr Assoc. 2023 Jul 10;111(3):684–94. DOI: 10.5195/jmla.2023.1588. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10361558/pdf/jmla-111-3-684.pdf.

4.      MEDLINE 2022 Initiative: Transition to Automated Indexing [Internet]. NLM Techincal Bulletin; 2021. Available from: https://www.nlm.nih.gov/pubs/techbull/nd21/nd21_medline_2022.html

5.      Rae AR, Pritchard DO, Mork JG, Demner-Fushman D. Automatic MeSH indexing: revisiting the subheading attachment problem. AMIA Annu Symp Proc. 2020;2020:1031–40. Epub 20210125. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8075546/pdf/139_3413087.pdf.

6.      Mork J, Jimeno Yepes A, Aronson A. The NLM Medical Text Indexer System for indexing biomedical literature. 2013. Available from: https://lhncbc.nlm.nih.gov/ii/information/Papers/MTI_System_Description_Expanded_2013_Accessible.pdf.

7.      Frequently Asked Questions about Indexing for MEDLINE: National Library of Medicine; 2023. Available from: https://www.nlm.nih.gov/bsd/indexfaq.html.

8.      Sticco A. NLM Office Hours: MEDLINE Indexing Update 2024. Available from: https://www.nlm.nih.gov/oet/ed/pubmed/02-24_oh_medline-automated-indexing.html.

9.      Aronson AR, Mork JG, Gay CW, Humphrey SM, Rogers WJ. The NLM Indexing Initiative's Medical Text Indexer. Stud Health Technol Inform. 2004;107(Pt 1):268–72. Available from: https://ebooks.iospress.nl/pdf/doi/10.3233/978-1-60750-949-3-268.

10. Fernandez-Llimos F, Negrão LG, Bond C, Stewart D. Influence of automated indexing in Medical Subject Headings (MeSH) selection for pharmacy practice journals. Res Social Adm Pharm. 2024 Jun 12. Epub 20240612. DOI: 10.1016/j.sapharm.2024.06.003.

11. Moore DAQ, Yaqub O, Sampat BN. Manual versus machine: How accurately does the Medical Text Indexer (MTI) classify different document types into disease areas? PLoS One. 2024;19(3):e0297526. Epub 20240313. DOI: 10.1371/journal.pone.0297526. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10936797/pdf/pone.0297526.pdf.

12. Brief Communication – concerning algorithmic indexing in MEDLINE. Journal of EAHIL. 2024 03/17 [cited 2025/04/09];20(1):18–21. DOI: 10.32384/jeahil20604. Available from: https://doi.org/10.32384/jeahil20604.

13. Wilson P. Sometimes the apple does fall far from the tree: a case study on automatic indexing precision errors in PubMed. J Med Libr Assoc. 2025 Oct 23;113(4):318–26. DOI: 10.5195/jmla.2025.2110.

14. Allen C, Carol H, Riley S, Deberg J. Developing an Author Checklist to Improve Discovery of Published Articles in the Era of Algorithmic Indexing. 2025. Zenodo. https://doi.org/10.5281/zenodo.17282091

Thanks for reading!

Culture Study Interview: How a Hospital Librarian Spends Their Days

 

Link to the article on substack.

Helpful Hint: I was looking for a link to a podcast -- audio -- and couldn't find one.  Turns out this is an interview with transcribed text, so once you follow the link to the website, scroll down past the usual podcast intro patter to read the "real" article / interview with Hospital Librarian Carrie Grinstad.  

You'll see a screenshot of a PubMed search strategy ...  That's about where the interview begins.  

Librarians are Tired of Being Accused of Hiding Secret Books that were Made Up by AI ...

Read the article on Gizmodo.  

NNLM Region 5 Blogs Highlighting Hospital Librarians

NNLM Region 5 spent National Medical Librarians Month highlighting librarians from throughout the region. Here's two of the posts highlighting hospital librarians in particular for your reading pleasure: 

From Nursing to Librarianship –Region 5 Blog about Frances Chu
From Nancy Drew to Literature Searches: the Case of the Medical Librarian – Region 5 Blog about Sola Whitehead.

More library and librarian profiles can be found at: News from Network Members – Region 5 Blog

The Hospital Library Caucus of MLA is updating its Resources for Hospital Librarians

 

The Hospital Library Caucus (HLC) of the Medical Library Association has released Version 2.0 of its LibGuide; a refreshed and expanded hub designed to support hospital librarians in their day-to-day work. Whether you’re managing a solo library, building clinical partnerships, or advocating for the value of library services, this updated guide offers streamlined access to essential tools, professional development resources, and support for demonstrating impact.

Read more in this recent MLA Connect article by Carlos Fernandez:

LibGuide 2.0: A Wickedly Good Resource for Hospital Librarians 

Hospital Library Caucus LibGuide Version 2.0: A Fresh Look at Resources for Hospital Librarians

It covers:

• What's New
• Why it Matters
• Who Should Use it 

Explore the updated Guide: Access Version 2.0.

The 2.0 site is still under construction, refer to Version 1.0.

Book Review: Malcolm Gladwell's Revenge of the Tipping Point

Over the Thanksgiving break, I listened to Malcolm Gladwell's Revenge of the Tipping Point.  When his original Tipping Point book celebrated its 25th birthday, the author decided to revisit some of those stories and correct some things he got wrong.  Instead, he wrote about some entirely new topics, several of which may be of interest to Health Science Librarians, including:

• How the Opioid Epidemic disproportionately affected certain areas of the US, and why?
• How a certain (very few) Prescribers are more susceptible to the undue influence of drug sales reps?
• Why parents with children in Waldorf schools are more likely NOT to get their kids vaccinated?
• How the local culture of a place affects behavior?
• Is teen suicide contagious?   And what factors can protect against it?

He covered a lot more than this short list -- In fact, it's amazing what he ties together.  This is just what I'm remembering off the top of my head a week later.

I borrowed the audiobook from my local public library and listened to it through the Libby App.  It was free, and they let me check it out for 21 days, rather than the previous default of just 7 days.  

New UX Blog Posts, and at least someone's enjoying the snow (Pets of WHSLA)!

MLA's User Experience (UX) Caucus has two new blog posts that I recommend checking out, especially if you happen to be a user of APA PsycInfo in the EBSCOhost interface:

• Controlled vocabular field codes and their discontents in EBSCOhost APA PsycInfo: This post discusses the frustrating limitations of controlled vocabulary field codes in EBSCOhost's APA PsycInfo (such as the fact that "there are zero field codes that search exclusively in the Subjects field associated with the APA Thesaurus"!). 

• Mismatched MeSH in EBSCOhost APA PsycInfo: This post explains and provides examples of how MeSH terms associated with records in EBSCOhost PsycInfo don't always match those in MEDLINE.

For those that celebrate, I hope everyone had a safe holiday last week! We received quite a bit of snow over in Madison, Wisconsin. While my husband and I weren't thrilled, our Irish wolfy, Hazel, took some enjoyment from the blizzard. Below is her sitting atop her throne.

Thanks for reading, and I hope everyone has a great week!