VerusCite: checking academic articles for hallucinations | Andrew Wheeler
About
C.V.
Datascience Portfolio
Dissertation
Comment Policy
Consulting
Courses
Advanced Criminology (Undergrad) Crim 3302
Communities and Crime (Undergrad) Crim 4323
Crim 7301 – UT Dallas – Seminar in Criminology Research and Analysis
Crime Science (Graduate) Crim 7381
GIS in Criminology/Criminal Justice (Graduate)
Crime Analysis (Special Topics) – Undergrad
Job Advice Resources
Code Snippets TOC
Andrew Wheeler<br>Crime Analysis and Crime Mapping
VerusCite: checking academic articles for hallucinations
I have a new app out, VerusCite. With the recent rise in popularity of GenAI tools like ChatGPT and Claude, this has also come along with academics writing slop articles.
One of the ways to check that slop is via looking at the articles citations. LLMs have some predictable failure modes in writing papers whole cloth – they tend to get details like complicated author lists wrong, or swap out incorrect journal titles. VerusCite is a tool for editors and reviewers to use to verify citations in a fast and cheap application.
It costs $2 to review a paper (and you get two free reviews on sign-up). If you want to see the output of a single example though, check out https://veruscite-data.com/share/E1-rn3TBwksENO_3hlmsRD0IG-EnXd6vfQg-upQZWQM
In addition to hallucinations, I have made many parts of the application just useful to editors in general. Many papers have minor errors in their bibliographies; typos, years off, author swaps, bad URLs, etc. Here is an example – no hallucinations that signal poor writing, but has seven different errors in the bibliography.
This is par for the course (it is quite possible 5% of citations have errors that look like this). The website has convenient tools to edit citations and export the fixed citations (whether minor errors or gross hallucinations) in various formats.
This makes much lighter work of the tedious job of formatting and checking citations for editors. One of the ways I think is critical to build generative AI tools is to consider the human in the loop from the start. My tool will ultimately make some errors (I error rate estimates in my public benchmark). I want it to be as fast for a human to confirm (or refute) the LLM label.
If you are an editor or a reviewer, I highly suggest you check the application out. Peer review journals (and pre-print servers that review the applications before posting), will need to use a tool like this as a first pass to ensure slop is not being posted.
Share this:
Share on X (Opens in new window)
Share on Facebook (Opens in new window)<br>Facebook
Share on LinkedIn (Opens in new window)<br>LinkedIn
Share on Pinterest (Opens in new window)<br>Pinterest
Like Loading...
Related
Leave a comment
by Andy Wheeler on August 5, 2026<br>• Permalink
Posted in data science, Python, scholarly, writing
Tagged LLM
Posted by Andy Wheeler on August 5, 2026
https://andrewpwheeler.com/2026/08/05/veruscite-checking-academic-articles-for-hallucinations/
Previous Post<br>Notes on document processing with LLMs
Leave a comment<br>Leave a comment Cancel reply
Search for:
Recent Posts
VerusCite: checking academic articles for hallucinations
Notes on document processing with LLMs
Podcast with Jeff Asher, AI blog posts
AI writing is better than no writing
Notes on Valuing the Cost of Crime
Categories<br>Categories<br>Select Category<br>art<br>ask me anything<br>Crime Analysis<br>Crime Mapping<br>Criminal Justice<br>data science<br>Data Visualization<br>excel<br>geocoding<br>ggplot2<br>healthcare<br>interval-censored<br>javascript<br>Macro<br>Mapping<br>Meta<br>Networks<br>NIBRS<br>Papers<br>Personal Productivity<br>Python<br>Regression<br>scholarly<br>social networking<br>SPSS<br>Stata<br>Tableau<br>Uncategorized<br>website<br>writing
Site RSS Feeds<br>RSS - Posts<br>RSS - Comments
Follow Blog via Email
Enter your email address to follow this blog and receive notifications of new posts by email.
Email Address:
Follow
Join 388 other subscribers
aoristic<br>big-data<br>cartography<br>census<br>choropleth<br>citeulike<br>consulting<br>cost-benefit<br>courses<br>crime-mapping<br>crime-trends<br>Crime Analysis<br>Criminal Justice<br>data-manipulation<br>data visualization<br>deep-learning<br>ESRI<br>excel<br>flow-data<br>folium<br>geocoding<br>github<br>google-streetview-api<br>grammar of graphics<br>group-based-trajectory<br>gun-violence<br>healthcare<br>homicide-rates<br>hot spots<br>hypothesis-testing<br>linear programming<br>LLM<br>logistic-regression<br>machine-learning<br>MACRO<br>mapping<br>matplotlib<br>meta<br>network<br>NetworkX<br>officer-involved-shooting<br>open-science<br>paper<br>Papers<br>peer-review<br>Poisson<br>prediction<br>Predictive-Policing<br>preprint<br>presentation<br>Python<br>Python-programability<br>pytorch<br>quasi-experiment<br>recidivism<br>regression<br>resources<br>scholarly<br>scraping<br>seaborn<br>shootings<br>simulation<br>small-multiples<br>social-media<br>social-networking<br>SPSS<br>stackexchange<br>Stata<br>statistics<br>survey<br>time-series<br>uncertainty<br>wdd<br>web-scraping<br>Top Posts & Pages<br>Group based trajectory models in Stata - some graphs and fit statistics<br>VerusCite: checking academic articles for...