Unverified50% confidenceFactExact time
Query fan-out refers to an LLM automatically generating multiple sub-queries when processing a user's question, retrieving information from different dimensions separately, and finally synthesizing them into an answer.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMulti-query retrieval uses an LLM to automatically generate 3–5 semantically equivalent but differently phrased variant queries for the same question, retrieves results for each separately, and takes the union to improve recall.69% similarUnverifiedA search engine is an indexing and ranking system that displays multiple sources for users to choose from, whereas an LLM is a synthesis and generation system that integrates and rewrites information before presenting it as a single answer.69% similarUnverifiedQuery Rewriting solves the problem of users' questions being colloquial and having unclear references, and common methods include using a large model to rewrite the question into a formulation more conducive to retrieval, expanding a single-turn question into multiple related sub-questions, and completing the context based on historical conversation.68% similarUnverifiedReal-time querying bypasses the cache layer and issues an actual query to the data source on every request, but places higher demands on the database's concurrent processing capability and query optimization.64% similarVerifiedIn the knowledge retrieval stage, the user's question is converted into a query vector via an embedding model, similarity is computed against the text chunk vectors in the knowledge base (typically using cosine similarity), and the top-K segments are returned by ranking.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1011966API
curl https://kongchang.com/api/v1/knowledge/claims/1011966MCP
get_claim(id=1011966)