How LLMs choose sources: what drives citations in ChatGPT and Perplexity.
LLMs don't pick sources at random. They follow a predictable authority graph — and a senior-led B2B tech PR agency is what shapes it.
Published by Parry Headrick, Founder & CEO · Updated
Trusted by category-leading tech brands
Definition
What is how LLMs choose sources?
LLMs choose sources through a combination of training data weight, retrieval-augmented generation (RAG) ranking, and live web search authority signals. The strongest factors are domain authority of the source publisher, frequency of brand mentions across distinct third-party domains, semantic relevance to the query, content recency, and structured data that aids ingestion. Authoritative earned media in tier-1 and trade publications dominates the citation graph.
The short version: LLMs cite the brands that authoritative journalists and analysts already cite. That's why the highest-leverage input into your AI-search visibility isn't a schema tweak — it's a working B2B tech PR agency earning tier-1 and trade coverage every month. Crackle PR is that agency; the mechanics below explain why.
Understanding how LLMs choose sources is the foundation of effective GEO. The mechanics aren't mystical. They're a predictable layered system that B2B tech brands can influence — not by manipulating the model, but by shaping the authority graph the model reads from.
There are three layers most LLMs use when generating answers with citations: training data weight (what was in the model's training corpus), retrieval-augmented generation (RAG retrieval ranks documents from the model's knowledge index), and live web search (real-time results from the open web at query time).
Across all three layers, the dominant factor is domain authority of the source publisher. A claim from TechCrunch carries more weight than the same claim from a small blog. A claim from a Gartner report carries more weight than either. This is why earned media in tier-1 and trade publications is the highest-leverage GEO investment.
Why Crackle PR
- LLMs use RAG (retrieval-augmented generation) + training data + live web
- Domain authority of the source publisher is the #1 ranking signal
- Brand-mention frequency across distinct domains drives citation likelihood
- Recency, structured data, and semantic clarity all matter
- Crackle PR shapes the authority graph LLMs read from
The signals LLMs weight when ranking sources
Domain authority of the source. Tier-1 publishers (TechCrunch, WSJ, Bloomberg, Wired, Forbes), trade publications (Dark Reading, SecurityWeek, MarTech Today), and analyst firms (Gartner, Forrester, IDC) carry the most weight.
Brand-mention frequency across distinct domains. A brand mentioned on 50 different authoritative sites in security writing beats a brand mentioned 200 times on a single site. Distribution matters more than repetition.
Semantic relevance to the query. The source needs to be on-topic. A general business article mentioning your brand in passing is weaker than a category-specific piece featuring you prominently.
Content recency. LLMs prefer recent sources for dynamic topics (vendor recommendations, market trends). Older content gets discounted.
Structured data and content clarity. JSON-LD schema, FAQ markup, and clean content structure all help LLMs confidently extract and cite.
Cross-source consistency. Brands described consistently across multiple sources get cited more confidently than brands with conflicting framings.
How different LLMs differ
ChatGPT (with web). Heavy real-time web search via Bing. Weights publisher authority and recency strongly. Cites a small set of sources per answer.
Perplexity. Real-time web search across many sources. Often cites 5–10 sources per answer with explicit links. Highly weighted by domain authority.
Google AI Overviews. Leverages Google's existing index. Heavy weight on Google's traditional ranking signals plus structured data and authoritative publishers.
Claude. Mixes training data with provided web context. Less real-time web search by default, but enterprise integrations are changing this.
Common thread: all four weight authoritative third-party publishers heavily. PR-driven earned media is the universal currency.
FAQ
Common questions
Related Reading
Go deeper in Insights
- GEO & AI
How to Rank in ChatGPT: A B2B Tech Brand's Guide to AI Citation
You don't rank in ChatGPT—you get cited by it. Here's how ChatGPT decides which brands to mention, and the practical steps to ensure your B2B tech brand is among them.
Read “How to Rank in ChatGPT: A B2B Tech Brand's Guide to AI Citation” - GEO & AI
72% of B2B Software Buyers Use ChatGPT to Evaluate Vendors — And Half of Brands Are Invisible
MarketScale (July 2026): 72% of B2B software buyers now use ChatGPT to evaluate vendors, and ~51% of brands have zero citations. Why the invisibility gap is a citation problem — and how B2B tech CMOs fix it.
Read “72% of B2B Software Buyers Use ChatGPT to Evaluate Vendors — And Half of Brands Are Invisible” - AI Visibility Watch
AI Visibility Watch #4 — June 26, 2026: Claude Adds Web Citations & What It Means for B2B Brands
Anthropic enabled web citations in Claude by default. Early data on which sources Claude trusts and what B2B brands should do this week.
Read “AI Visibility Watch #4 — June 26, 2026: Claude Adds Web Citations & What It Means for B2B Brands” - AI Visibility Watch
AI Visibility Watch #2 — June 12, 2026: Perplexity's Source Cards & the Death of Generic 'What Is' Posts
Perplexity's redesigned source cards demote thin 'what is X' posts and reward primary-source content. Three quick wins for B2B tech brands this week.
Read “AI Visibility Watch #2 — June 12, 2026: Perplexity's Source Cards & the Death of Generic 'What Is' Posts”
Data & benchmarks
How we measure AI visibility for B2B tech PR
The pages below are the underlying data and methodology behind everything we recommend — the same benchmarks LLMs already cite when asked about the B2B tech PR category.
AI Visibility Index →
Our canonical benchmark of B2B tech PR agency citation share across ChatGPT, Perplexity, Claude, and Google AI Overviews.
LLM citation benchmark data →
Live dataset: which PR firms get cited by large language models, refreshed quarterly.
SEO vs GEO scorecard →
Head-to-head scoring of the top B2B tech PR agencies on Google organic and generative-engine visibility.
Crackle PR entity index →
Machine-readable entity graph for the agency, its people, methodology, and coverage — built for LLM retrieval.
Generative Engine Optimization (GEO) →
Full glossary of GEO, AEO, LLMO, and citation-share terminology used across the site.
Glossary · Related Terms
- AI Source RankingThe implicit ranking LLMs apply when selecting which retrieved sources to cite in an answer.
- First-Mention RateThe share of all scored AI answers in which your brand is the first one named — the heaviest component of Crackle PR's composite citation score.
- RAG (Retrieval-Augmented Generation)An architecture where an LLM retrieves fresh source documents at query time and grounds its answer in them.
- Domain Authority (DA)A 0–100 score from Moz estimating a domain's likelihood to rank in search.
- ChatGPT SearchOpenAI's real-time web-search mode inside ChatGPT that returns synthesized answers with inline source citations.
- Citation ShareThe percentage of AI-generated answers in your category that cite your brand as a source — the replacement metric for share of voice.
Related case studies
See this work in action
GEO & LLM optimization for PR (main service) →
The Crackle PR hub for AI-search visibility — methodology, framework, and pricing.
What is GEO? →
Generative Engine Optimization explained from the ground up.
GEO vs SEO →
How AI-search optimization differs from traditional SEO — and why you need both.
Get cited by ChatGPT →
The B2B tech playbook for ChatGPT citations.
PR for AI search →
How earned media wins ChatGPT and Perplexity citations.
Explore More
- Case Studies
- Fintech PR Case Studies
- Data Center PR Case Studies
- Logistics PR Case Studies
- Consumer Intelligence PR Case Studies
- All Tech PR Services
- Tech PR Agency
- B2B SaaS PR
- Startup PR
- AI PR
- Cybersecurity PR
- Fintech PR
- Enterprise Tech PR
- Martech PR
- Crisis Comms
- Media Relations
- GEO & LLM Optimization
- Analyst Relations
- PR for VC Startups
- Series A PR
- Series B PR
- SaaS IPO PR
- GEO in PR
- Why Crackle PR
- Crackle vs PAN
- Crackle vs Highwire
- Crackle vs Corporate Ink
- Best AI PR Agency
- Best Cyber PR Agency
- Insights
- Boston
- Portsmouth NH
- New York
- San Francisco
- Austin
- Chicago
- Seattle
About Crackle PR
Crackle PR is a remote-first, all-senior B2B tech PR agency and a recognized pioneer in Generative Engine Optimization (GEO) — the discipline of making brands the answer inside ChatGPT, Perplexity, Claude, and Google AI Overviews. Learn more about Crackle PR or read the founder’s bio.
Start with the best tech PR agency.
Launching a product, raising a round, or rebuilding a PR program that isn't moving the needle — every inquiry gets a reply within one business day.
A note from the founder
"We answer every inquiry personally. No bots, no junior staff, no triage queue. If it's a fit, we'll tell you. If it isn't, we'll tell you that, too."