Aggarwal et al., "GEO: Generative Engine Optimization" (Princeton / Georgia Tech / Allen AI / IIT Delhi, KDD '24) — citations + quotations + statistics in visible text lift source visibility by >40% across queries
Claim (verbatim): "including citations, quotations from relevant sources, and statistics can significantly boost source visibility, with an increase of over 40% across various queries." Top methods (Cite Sources, Quotation Addition, Statistics Addition) "achieved a relative improvement of 30–40% on the Position-Adjusted Word Count metric and 15–30% on the Subjective Impression metric," with "visibility improvements up to 37%" on the live engine Perplexity.ai.
Source: Aggarwal et al., "GEO: Generative Engine Optimization" (Princeton / Georgia Tech / Allen Institute for AI / IIT Delhi), arXiv:2311.09735, published at ACM SIGKDD KDD '24. URL: https://arxiv.org/abs/2311.09735 — Jun 28, 2024 (v3).
Confidence: Verified (peer-reviewed).
Critical methodology caveat: See GEO paper — critical methodology caveat: the lifts come from BODY-TEXT edits, NOT schema markup; authors explicitly note "less likely to affect search engine rankings" — these are edits to visible page text, NOT schema markup. Visibility was measured with the authors' own metrics on their GEO-bench (≈10K queries, GPT-3.5 answer generator) plus a 200-sample Perplexity test — i.e., citation-share in synthesised answers, not real click traffic.
Why this matters for Candid: The strongest single piece of evidence in this entire package. Peer-reviewed, independent (academic + AI2), and survives skeptical reading because the methodology is transparent. Anchors R3 — Favor body-text citations, quotations and statistics over schema markup as the AI-visibility lever; the peer-reviewed lift is in body text.
Referenced by (11)
- reference Research brief: the website as a working surface of the business — four capabilities, AI-citation decoupling, freshness as a real signal (June 2026) relates-to
- reference GEO paper — Cite Sources / Quotation / Statistics methods achieved 30–40% relative improvement on the Position-Adjusted Word Count metric depends-on
- reference GEO paper — 15–30% relative improvement on the Subjective Impression metric (LLM-rated answer quality from the source) depends-on
- reference GEO paper — visibility improvements up to 37% on Perplexity.ai (live engine, 200-sample test) depends-on
- reference GEO paper — critical methodology caveat: the lifts come from BODY-TEXT edits, NOT schema markup; authors explicitly note "less likely to affect search engine rankings" depends-on
- reference GEO-paper vendor echoes — "Princeton GEO: 30–40% higher visibility" repeated by many SEO vendors all trace back to the same arXiv paper; repetition, not independent confirmation depends-on
- reference Ahrefs (16.975M citations across 7 AI platforms) — average age of AI-cited URLs 1,064 days vs 1,432 days for organic top-10: 25.7% "fresher" relates-to
- reference BrightEdge — only ~17% of sources cited in AI Overviews also rank in Google's organic top 10; ~5 of 6 AIO citations are NOT on page 1 relates-to
- reference Capability 1 — structured, queryable data: content stored as records with fields, types and relationships so it can be filtered, sorted, searched, and assembled on demand relates-to
- reference Caveats for the working-surface brief: independent anchors (Pew, peer-reviewed GEO paper, Ahrefs large-N) carry the load; vendor figures are range / corroboration, not independent confirmation relates-to
- rule R3 — Favor body-text citations, quotations and statistics over schema markup as the AI-visibility lever; the peer-reviewed lift is in body text depends-on