Skip to content
Waseit
← All articles
AEOGEO

134 wrong answers out of 200, 15 doubts expressed: being cited is not being cited correctly

Two major studies measured AI engine citations. More than 60% are incorrect, 31% have a sourcing problem, and the confidence never drops. What that changes for a brand.

more than 60%

of citations incorrect across 1,600 queries, eight engines tested (Tow Center, March 2025)

September 5, 20269 min read
In this article
  1. What two major studies measured
  2. The worst part is not the error, it is the confidence
  3. Links that lead nowhere
  4. What this changes for a brand
  5. What this changes

Short answer: an AI citation can name you and get you wrong. The published measurements are not about appearing, but about the accuracy of what is attributed: more than 60% incorrect citations in a study of 1,600 queries, 31% with sourcing problems in another covering more than 3,000 responses. The useful question is therefore not only « am I cited », but « is what I am made to say true, and does the link go anywhere ».

31%

of responses with a sourcing problem - missing, misleading or incorrect attribution (EBU and BBC, October 2025)

134 against 15

articles misidentified by ChatGPT, against the number of times it flagged a doubt, across 200 responses

An engine that is wrong and says so leaves you a chance. An engine that is wrong with confidence leaves none: the reader has no reason to go and check.

What two major studies measured

The first comes from the Tow Center for Digital Journalism at Columbia, published on 6 March 2025. The protocol is simple and reproducible: twenty publishers, ten articles drawn at random from each, excerpts copied verbatim, and eight answer engines asked to identify the headline, the original publisher, the date and the URL. That is 1,600 queries. Collectively, the engines returned an incorrect answer to more than 60% of them.

Incorrect citations, eight answer engines, 1,600 queries (Tow Center, 6 March 2025). The per-engine figures quoted here are the ones the study states explicitly.
MeasureResult
All eight engines togethermore than 60% incorrect answers
Perplexity, best of the panel37% incorrect
Grok-3, worst of the panel94% incorrect
Grok-3, citations leading to an error page154 out of 200

The second is broader and comes from public service media. Published on 22 October 2025 by the European Broadcasting Union with the BBC, it had professional journalists evaluate more than 3,000 responses from ChatGPT, Copilot, Gemini and Perplexity, across 22 organisations, 18 countries and 14 languages. Its central conclusion is that the failure is systemic: it is tied neither to language, nor to market, nor to any one assistant.

Faults recorded by journalists across more than 3,000 responses, 22 public service media organisations, 18 countries, 14 languages (EBU and BBC, 22 October 2025).
Type of faultShare of responses
At least one significant issue45%
Sourcing problem: missing, misleading or incorrect attribution31%
Major accuracy issue: invented details, outdated information20%
Gemini, responses with a significant issue76%

The worst part is not the error, it is the confidence

One figure from the Tow Center deserves isolating, because it decides everything else. ChatGPT misidentified 134 articles out of 200, and signalled a lack of confidence only fifteen times. Error and doubt are not correlated: the engine is wrong in two thirds of cases and says so in one case out of thirteen.

That is the difference between a fallible source and a misleading one. An engine that hesitates leaves the reader a signal, and therefore a chance to check. An engine that asserts leaves nothing. For a company it means an erroneous citation does not correct itself: nothing in the answer invites anyone to doubt it.

Links that lead nowhere

The other finding is more concrete still. More than half of the responses from Gemini and Grok-3 pointed to fabricated or broken URLs. For Grok-3, 154 citations out of 200 landed on an error page. The engine does not merely misattribute: it invents an address that has the appearance of proof.

The EBU study describes the same mechanism on the sourcing side: claims attributed to newsrooms that had never made them, links leading to an article on a different subject or to a page that no longer exists, and sometimes a complete citation - outlet name, headline, date - for an article that was never published. A well-formed reference is not a true one.

What this changes for a brand

The reasoning transfers directly. If an engine can attribute a sentence to a newsroom that did not write it, it can attribute your argument, your price or your speciality to a competitor - or the reverse, credit you with a promise you never made. In both cases you are « cited », and in both cases a counter that merely counts citations reports good news.

That is the limit of a visibility score taken alone, ours included. Appearing is a necessary condition, it is not the measure of the outcome. A citation is read with three questions: are we named, is what is attributed to us accurate, and does the offered link lead to a page that exists.

  • These studies are about news, not about business recommendations.

    The Tow Center protocol is to trace the origin of a press excerpt; the EBU one has journalists evaluate news answers. The attribution mechanism is the same, but the transfer to commercial recommendations is ours and was not measured by this work.

  • They date from 2025, and the models have changed since.

    The Tow Center published in March 2025, the EBU and the BBC in October 2025. The versions tested are no longer the ones served today, and neither measurement says what the same protocol would give this month. We have not redone it.

  • An average across eight engines hides enormous gaps.

    Between 37% and 94% errors depending on the engine, the global « more than 60% » is an average that the worst performer lifts. Quoting that single figure to describe one particular engine would be a reading error.

  • We reproduced neither of them.

    These are works published by a university research centre and by a consortium of public service media, read at source. They are not our measurements, and we do not present them as such.

What this changes

Read the citation, not just the counter.

Being named and being well described are two different outcomes. A dashboard that counts only appearances cannot tell good news from an error about you.

Check that the link exists.

An invented address on your domain looks like proof and is not. Click what the engine offers: half the responses from two tested engines led to a dead page.

Watch what is attributed to your competitors.

The error runs both ways: your argument can be credited to another name, and that is invisible from monitoring that only watches yours.

Do not count on the engine's doubt.

It is wrong far more often than it hesitates - 134 errors against 15 reservations across 200 responses. A confident tone says nothing about the accuracy underneath.

Frequently asked questions

Can an AI citation harm my business?
Yes, and it is the point visibility counters miss. The published studies record claims attributed to sources that had never made them, and links leading to pages that do not exist. Transferred to a brand, that means an answer can credit you with a price, a speciality or a promise that is not yours, while still counting you as cited.
Which engine cites most accurately?
In the Tow Center study of March 2025, Perplexity was the best of the panel with 37% incorrect answers, and Grok-3 the worst with 94%. Two caveats apply: those versions are no longer the ones served today, and 37% error remains a high rate. No engine in the panel was reliable in the ordinary sense of the word.
How do I check what an AI says about us?
Ask the question the way a customer would, then read the answer in three steps: does your name appear, is what is attributed to you accurate, and does the offered link lead to a page that exists. Repeat the measurement over time, because one day's answer does not predict the next. That is what our monitoring does, and it is also what you can do by hand.