Say hello to the new Saazy! See what’s new ✨

AI Doesn’t Just Read Wikipedia, Wikipedia Stabilizes Your Name

Date

Author

Executive summary (the part you can read in 60 seconds)

Lead: “Why don’t chatbots know us?”

Picture this: your team rolls out an AI assistant on your website. A customer asks about your company. The bot answers like you don’t exist.
So you test it yourself. You type your company name.
Nothing.
Then someone tries a slightly different version maybe with “Inc.”, maybe without parentheses, maybe the old brand name, maybe the domain name.
Suddenly the bot “knows” you.
That’s the twist: the model may know your organisation, but not the exact string you typed.
This is a canonical-name failure:
Small string variations → big recognition swings.

What we measured (and why this dataset is different)

This comes from the LLMtel benchmark, which tested “AI visibility” at scale:

The study uses two scores. They sound similar, but they measure different things.

Metric 1: Entity Score “Does the AI know this name?”

This score answers one question:

“If we directly ask each AI about this entity, how many of them recognize it?”

We tested 17 different LLMs, so the score is always out of 17.

Example:
If 14 out of 17 models know the entity:

This tells you how familiar the models are with the entity when asked directly.

Metric 2: Questions Score “Does the AI mention this name on its own?”

This score answers a different question:

“When we ask many questions across many models, how often does this entity show up in the answers?”

The math:

Then:

Example:
If an entity appears 74 times in 170 possible answers:

This tells you how likely the AI is to bring up the entity by itself in real conversation.

The canonical-name failure: what it is, and why it breaks AI visibility

Canonicalization means: turning a messy real-world name into one stable identity.
In practice, it’s normalizing things like:

Why it matters
If your identity is split across variants:

Common failure modes (seen constantly in real life)

The proprietary proof: normalization pairs that split signal

The dataset includes normalization pairs: two surface-name variants that humans clearly understand as the same entity, but models treat differently.
Here’s the simplest way to quantify the damage:

For any two variants of the same entity:

So losing 3 models is:

A) PRSA variant penalty (punctuation broke recognition)

Math:

Interpretation: one missing “)” corresponded to a 3-model recognition drop.

B) CMA variant penalty (formatting moved the needle)

Math:

Interpretation: one missing “)” corresponded to a 3-model recognition drop.

C) Smaller brands show the same pattern
This is not only a “big brand” phenomenon.

Why Wikipedia is the stabilizer(the “entity identity resolver” argument)

Here’s the point most people miss:
Wikipedia doesn’t just describe entities. It standardizes them.
Think of Wikipedia like the DNS system for names:

LLMs learn patterns from huge text corpora. When the same entity is repeatedly presented with

…the model has a much easier time “grounding” the name.

Redirects matter because they teach:

“These different strings point to the same entity.”

That is exactly what your normalization pairs show models struggle with when that resolver layer is missing.

Why Wikipedia is the stabilizer(the “entity identity resolver” argument)

Even if a model vendor says “we don’t train directly on Wikipedia,” Wikipedia-derived content is:

So Wikipedia’s naming decisions leak into the wider training environment.

Note:
Entity recognition improves when the model sees repeated co-occurrences:

The bigger pattern: visibility is a pipeline (Known vs Named)

Canonical naming is the identity layer. But visibility also depends on question intent and context.
The 1,000-entity study shows two big buckets:
Known but never named

What this means

Wikipedia helps with identity. It doesn’t guarantee recommendation.

Practical implications for executives

If you run a brand or organization
Treat naming consistency like infrastructure, not marketing copy.
If your identity is split across variants:

If you use AI visibility rankings
Be careful: “AI awareness” metrics can be wrong if the scoring doesn’t normalize variants.

Wikipedia helps with identity. It doesn’t guarantee recommendation.

Playbook: how to stabilize your name for AI (ethically)

List every variant people use:

Choose one “primary” display name and lock it:

Use it everywhere:

If eligible and appropriate:

Rebrands, product lines, and global naming differences create new variants. Track them quarterly.

 Conclusion

AI doesn’t “forget” you. It often fails to map you.
Wikipedia’s superpower is not fame. It is canonicalization:

If you care about being findable in LLM answers, treat naming consistency like infrastructure.

Leave a Reply

Your email address will not be published. Required fields are marked *