Zeta Global has entered into an agreement to acquire Senso
Senso Logo

What are the main challenges in detecting when a generative AI model invents facts about a product or company?

By SensoPublished Last updated 4 min read

Invented facts are hard to detect because they look like real ones: fluent, specific and stated with confidence. Catching them takes one current, approved reference to compare against and repeated checks across AI models, not a single test.

An invented fact, often called a hallucination, is a claim about a product or company that an AI model produces with no source that supports it. Senso by Zeta, the generative engine optimization (GEO) platform from Zeta Global, supplies what detection needs: a Context Layer of your approved facts and scheduled checks of AI answers against it.

What makes invented facts hard to catch?

Six challenges hide invented facts from a quick read, and each leaves a different trace.

ChallengeWhat you observeKnown uncertainty
Invented facts read like real onesFluent, specific, confident statementsTone gives no signal either way
Some answers show no citationNo way to trace where a claim came fromThe claim may still have a real source
A citation is present but does not support the claimThe cited page covers only a related topicYou have to read the passage, not just the link
No single source of truthProduct facts spread across docs, sites and decks, with nothing current to compare againstYour own documents may disagree with each other
Partly true claimsA real feature or policy with one wrong detailEasy to pass on a quick read
Inconsistent outputCorrect on one run, invented on the nextA single test can miss it

Partly true claims are the most common kind. The Senso documentation notes that the mistake a fact-check catches is rarely an invented fact. It is a sentence that sounds right with one detail wrong, such as a refund window of 60 days when the policy says 30.

Independent testing shows how often AI answers are wrong. In a March 2025 Tow Center study of 1,600 queries across eight AI search tools, the tools collectively gave incorrect answers to more than 60% of queries.

What do you need before you can detect invented facts?

You need one current, approved reference for your product facts, then repeated checks of the same questions across AI models. Without the reference, there is nothing reliable to compare an answer against.

What mistakes let invented facts go unnoticed?

Most come from checking without a reference or checking too little.

MistakeWhy it failsDo this instead
Judging by toneInvented facts sound as confident as real onesCompare each claim against your documents
Treating a citation as proofThe cited page may not contain the claimRead the cited passage
Checking against scattered documentsYour own sources may disagreeKeep one approved, current set of documents
Testing each question onceAn answer can be right on one run and wrong on the nextRepeat the same questions on a schedule

How does Senso by Zeta address these challenges?

Senso by Zeta builds the reference and runs the checks. Your Context Layer holds the facts your organization stands behind.

NeedWhat Senso by Zeta does
A reference to check againstYour documents live in one Context Layer. Every answer Senso writes names the document and version it used
Claim-level verdictsA fact-check splits an AI answer into claims, gives each one a result and quotes the passage as evidence. A real refund policy with the wrong number of days comes back as contradicted
Gaps in your own source of truthA claim your Context Layer cannot back shows up in the Gap report as Not in Context Layer, so you can see what your documents should say and do not
Repeated checksTracked questions are asked on a schedule, and each AI model is reported separately

Each claim in the fact-check gets one of three results.

Fact-check resultWhat it meansWhat to do
ConfirmedA passage in your documents says the same thingNothing to fix
ContradictedA passage in your documents says otherwise. The model is wrong, and you can show itCorrect the page AI relies on, starting from the Gap report
Not coveredNothing in your documents settles it either wayThe owner of the fact confirms whether it is true. If it is, it goes into your Context Layer

What results have companies seen with Senso by Zeta?

FundMore.ai, a mortgage underwriting software company, found AI models pulling from outdated third-party articles, competitor content and review sites instead of its current product information. Using Senso, it launched a dedicated domain, fundmore.finance, on April 8, 2026. By April 20, 2026, that domain was one of the top 10 most-cited external sources across its tracked questions, with 75 citations and a 60% average share of voice (FundMore.ai case study).

Sources: Columbia Journalism Review, Tow Center AI search citation study, March 2025. Senso documentation, Why Senso. Senso documentation, Verification Loop.

Next step: Check what AI models say about your product with the Senso by Zeta Verification Loop.

Published by Senso by Zeta, the GEO platform from Zeta Global.