Concept查询扇出 / Query Fan-out
Query Fan-out
A retrieval architecture introduced by Google in AI Overviews. The user's original query is split into multiple semantically related sub-queries, which are retrieved separately and then merged, with the results assembled by a large model into a synthesized answer. It draws on ideas from query expansion and multi-hop retrieval.
Timeline (last 90 days)
Oct 16
The difference between Query Fan-out and traditional query rewriting and query expansion is that the latter two generally still revolve around a single retrieval intent, whereas fan-out breaks a question into multiple mutually independent sub-queries executed separately, retrieving from different data sources and then integrating the results.
Unverified50%