Guides

Does Perplexity make up sources?

Sometimes, yes. Perplexity shows a link for each source, but published tests still catch it citing wrongly. In a 2025 Tow Center test on news articles, it answered 37% of queries incorrectly. A 2025 study of academic references put it among the chatbots with the highest hallucination rates. Open every source and read the cited passage before you use it.

Evidence last checked:

Two different ways a citation goes wrong

An invented source points to a page or paper that does not exist. A real but unsupported source exists, but does not say what the answer claims. Perplexity's links make the first kind easier to spot; the second kind only shows up when you read the page.

A third pattern from the Tow Center test: the right article, but a copy. Perplexity Pro cited syndicated versions of Texas Tribune articles for three of ten queries. For a thesis, cite the original publisher, not a republished copy.

What the two studies actually tested

Only the Cabezas study tested a thesis-style prompt on Perplexity, and it tested the free version in February 2025. The Tow Center study used news articles. The Tow Center asked for the headline, publisher, date and URL of news excerpts. The arXiv study asked free chatbots to generate academic references from a prompt. Read the scope column before you repeat a number.

Published tests that include Perplexity, opened 16 October 2026
StudyWhat it foundScope limit
Tow Center / CJR (Jaźwińska & Chandrasekar, 6 Mar 2025): 8 AI search tools, 1,600 queriesDossierSource 1“Perplexity answering 37 percent of the queries incorrectly, while Grok 3 had a much higher error rate, answering 94 percent”. Premium versions answered more prompts correctly but also gave more confidently wrong answers.News articles, not academic papers. The authors say the findings “are not intended to be extrapolated to all models or news organizations”.
Cabezas-Clavijo & Sidorenko-Bautista (arXiv 2505.18059, 2025): 8 free chatbots, 400 academic referencesDossierSource 1In a February 2025 test of free chatbot versions (arXiv 2505.18059), researchers asked each tool for 50 academic references in APA style across five subjects; 72% of the 50 references from Perplexity (free version, Sonar model) were wrong or fabricated; across all eight chatbots, 39.8% were erroneous or entirely fabricated. That is not an error rate for Perplexity's answers or links today.Free versions generating references from a prompt; tested 7–9 Feb 2025. We read the full paper.

Check a Perplexity source in two minutes

Open the link. Find the sentence that supports the claim; if you can't, the citation fails. For a paper, search the exact title in a scholarly index and resolve the DOI. Cite the original publisher, not an aggregator or copy.

Before you paste in your own draft

Perplexity can use content from Free, Pro and Max accounts for model training: “AI Data Retention” is on by default. Turn it off under Account settings > Preferences > AI data retention. The opt-out only covers data collected after that date; previously collected training data cannot be removed.

Questions this guide answers

Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.

Does Perplexity make up sources?

Sometimes, yes. Perplexity shows a link for each source, but published tests still catch it citing wrongly. In the Tow Center test of news citations, Perplexity answered 37% of queries incorrectly, and its Pro version cited republished copies instead of originals. Open every link and find the sentence that supports your claim.

Is Perplexity accurate for academic research?

One published test used a thesis-style prompt: in February 2025, researchers asked the free version of Perplexity (Sonar model) for 10 APA references per subject for a final degree project, and 72% of its 50 references were wrong or fabricated (arXiv 2505.18059). The 37% figure is from news articles. Use Perplexity to find leads, then confirm each paper in a scholarly index.

Is Perplexity Pro more reliable?

Not clearly. In the Tow Center test, premium tools answered more prompts correctly than their free versions but also gave more confidently wrong answers instead of declining.

How do I check a Perplexity citation?

Open the link, find the sentence that supports the claim, and cite the original publisher. For papers, match the exact title in a scholarly index and resolve the DOI.

Does Perplexity train on my searches?

It can on Free, Pro and Max accounts: “AI Data Retention” is on by default. Turn it off under Account settings > Preferences > AI data retention. The opt-out only covers data collected after that date.