Observation · Perplexity

How do AI search engines choose which sources to cite?

Perplexity separated retrieval from citation: engines first find and rank candidate sources, then cite passages that support specific claims, without publishing a universal weighting formula.

15 November 2026, 18:08 CSTen-US (English answer; zh-CN interface)Run 3 of 3Method v0.1
Question

Recorded prompt

“How do AI search engines choose which sources to cite?”
Product
Perplexity
Surface
Perplexity Search with web search enabled
Model
Perplexity automatic model (model version not exposed)
Locale
en-US (English answer; zh-CN interface)
Observed answer
Open session ↗
Observed
15 November 2026, 18:08 CST
Fresh conversation
Yes
Answer snapshot

What the answer said

Perplexity described source selection as query interpretation and search fan-out, retrieval and ranking, identification of passages that support the answer, then attribution. It said citation selection is related to search ranking but is not merely the ordinary results list. It highlighted exact-question relevance, passage-level support, reliability, accessibility and eligibility, freshness and extractable content, while noting that platforms do not publish a complete weighting formula. It warned that a retrieved page is not necessarily cited.

Linked citations

3 recorded sources

Limitations

What this observation cannot show

Authenticated free-account run in a fresh Perplexity conversation. The rendered answer exposed three linked source URLs; the consolidated source panel did not populate during capture.