GEO Visibility
GEO Visibility
AI visibility intelligence
FeaturesBlogAbout
Log in
All posts
Engine Research4 min read

Content patterns that actually get cited — what 30M ChatGPT responses tell us

The Princeton GEO paper measured +40% citation lift from three specific moves. The Profound 30M-response study found 44% of citations come from the first 30% of content. Here's what the data says about shape, structure, and density — and what to stop doing.

GEO Visibility Research
Published May 7, 2026

There are now two well-instrumented studies that tell you what shape of content AI engines pick up. Both are primary research with stated methodology — not vendor blog handwaving.

This post compresses them into a checklist.

Study 1 — Princeton GEO (KDD 2024)

Aggarwal et al. ran a 10,000-query benchmark across a Perplexity-style retrieval engine and measured the Position-Adjusted Word Count lift from nine different content interventions. Citation: arXiv:2311.09735.

The headline result, verbatim from the paper (numbers are maximum lift observed on the highest-responsive query subset, not averages — the paper is explicit that effects vary by domain and position):

InterventionPosition-Adjusted Word Count lift
Cite sourcesup to +40%
Quotation additionup to +40%
Statistics additionup to +40%
Fluency optimization + Statistics addition (combined)+5.5% over any single method
Cite sources on a position-5 result+115%
Keyword stuffing (control)negative — actively decreased visibility

Translation: the three highest-leverage moves are (1) cite primary sources inline, (2) drop direct quotes from named authorities, and (3) include verifiable statistics. The marginal lift drops fast — adding all three doesn't give you +120%, it gives you ~+45%. Pick the right one per page. Median lift across all queries is significantly lower than the +40% headline — treat the table as ceiling, not expected value.

Domain-conditional findings:

  • Statistics addition dominates on Law/Government and Opinion-type queries.
  • Quotation addition dominates on People & Society, Explanation, and History.
  • Cite sources is the highest-leverage move for lower-ranked pages — if you're at position 4-6 on Google for the underlying query, this is the +115% intervention.

Keyword stuffing was the only intervention with a negative Subjective Impression score. Old-school SEO over-optimization actively hurts in generative engines.

Study 2 — Profound, 30M ChatGPT citations (Sep 2025)

Profound analyzed 3M ChatGPT responses and 30M citations, 18,012 of which they verified by hand. Source. The hand-verified subset is 0.06% of the corpus — directional signal, not a controlled experiment, and the cohort skews toward Profound's own customer prompts. Treat the percentages below as patterns we've also seen in our own audit logs, not as a peer-reviewed measurement.

The unintuitive findings, verbatim:

  • 44.2% of citations come from the first 30% of a document. They call this the "ski ramp" — steep drop after the first third, long tail to the bottom.
  • 53% of citations come from the middle of paragraphs. Only 24.5% from first sentences and 22.5% from last sentences. Front-loading every key insight to the opening sentence is wrong. Uniform information density beats positional gymnastics.
  • Proper-noun density of cited text averages 20.6% — vs typical English at 5-8%. A 3-4× concentration of named entities (brands, people, places, products).
  • 78.4% of citations tied to questions came from headings in question form (H2/H3 as questions).
  • Cited content was 2× more likely to contain a question mark anywhere.
  • Flesch-Kincaid grade level of cited content averaged 16 vs 19.1 for non-cited. Plainer prose wins, not denser academic prose.

Translating the data into a checklist

If you want one paragraph that touches every variable both studies converge on:

Open with a named entity. Drop a statistic with its source link. Use a question as your next H2. Keep paragraphs uniform in density — don't dump everything in the first sentence. Aim for grade-16 prose, not grade-19.

Concretely, here's the checklist we run pages through inside our audit:

  1. Front 30% audit — does the first third of the page contain the named entities, statistics, and quotes you want cited? If they're in the conclusion, move them up.
  2. Proper-noun density — count proper nouns / total tokens. Below 12% is under-optimized. Above 25% reads like a press release.
  3. Question-form headings — at least one H2 should be a question. Aim for 30-50% of H2/H3 in question form.
  4. Statistic density — at least one verifiable, source-linked number per 500 words.
  5. Reading grade — target Flesch-Kincaid 14-18. Higher than 19 hurts you in retrieval reranking.
  6. Citation links — inline <a> tags to primary sources, not vague "studies show" phrasing.

What does not move citations (despite vendor claims)

A pattern across 2026 vendor blogs is to claim 1.4-3.2× lifts for "freshness," "FAQ schema," "long-form content." Those numbers don't appear in primary research:

  • "Long-form wins" — Ahrefs' Dec 2025 study found 53.4% of AI Overview citations go to pages under 1,000 words. Average cited length: 1,282 words. Length is not the lever; density and structure are.
  • "FAQ schema lifts citations 44%" — no published methodology. Empty schema can actively hurt (our detectHtmlMismatches() audit catches this).
  • "Freshness × 3.2" — fresh content does help, but the multiplier is closer to 1.2-1.4 in AI Overviews per the Ahrefs Q1 2026 data, not 3.2.

Optimize for what the primary studies measured. Skip claims with no methodology link.

Sources

  • Princeton GEO paper (KDD 2024) — https://arxiv.org/abs/2311.09735
  • ACM record — https://dl.acm.org/doi/10.1145/3637528.3671900
  • Profound 30M citation study — https://www.tryprofound.com/blog/ai-platform-citation-patterns
  • Ahrefs short vs long content — https://ahrefs.com/blog/short-vs-long-content-in-ai-overviews/

Want the checklist applied to your pages? Run a free audit — our citability analyzer scores the front-30% concentration, proper-noun density, question-heading ratio, and reading grade for every crawled page.

GEOCitationsContent StrategyPrinceton GEO
Share

Want this analysis for your site?

Our free audit runs the same checks across ChatGPT, Claude, Gemini, Perplexity, and Claude — 9 analyzers, ~3 minutes, no sign-up required.

Run free audit

Like this post? Get the next one.

One email per new piece of research. Engine-by-engine field notes, primary-sourced.

We use your email only for new-post notifications. Unsubscribe in one click.

Keep reading

Related posts

All posts →
Engine Research5 min

What every AI engine actually cites in 2026 — engine-by-engine field guide

May 10, 2026
Playbooks6 min

What is GEO? A plain-English guide to Generative Engine Optimization

May 20, 2026
Playbooks4 min

llms.txt: the honest guide — what it is, who reads it, and whether you should ship one

May 9, 2026
On this page
  • Study 1 — Princeton GEO (KDD 2024)
  • Study 2 — Profound, 30M ChatGPT citations (Sep 2025)
  • Translating the data into a checklist
  • What does not move citations (despite vendor claims)
  • Sources
GEO Visibility
GEO Visibility
AI visibility intelligence

Track how ChatGPT, Claude, Gemini, and Perplexity talk about your brand, then turn those gaps into action.

A Product of AI Guru®

Product

  • Features
  • Blog
  • About

Intelligence

  • AI Visibility Tracking
  • Multi-region tracking
  • Cross-page schema coverage
  • Citation Intelligence
  • Localization Signal Score
  • Social Listening
  • Brand memory

Company

  • Privacy Policy
  • Terms of Service
  • [email protected]

© 2026 GEO Visibility. All rights reserved.

Built for operators monitoring AI search visibility, citations, and answer-engine share of voice.