Skip to content
AImpact
IT EN
Infrastructure Advanced

Cross-encoder vs bi-encoder

Two architectures to measure text similarity: the bi-encoder encodes query and document separately (fast), the cross-encoder processes them jointly (slow but accurate).

ShareLinkedInX

In practice

Bi-encoder = precomputed embeddings, used for the first search over millions of documents. Cross-encoder = score computed on the fly over few candidates, used as a final reranker. They are complementary, not alternatives.

Related terms

Embedding Reranker RAG

Seen in the wild

0 entries mentioning it

No archive entry mentions it explicitly. Appears in broader contexts.

← All terms