Cross-Encoder
Model that scores a query and a passage together in one forward pass.
Overview
A cross-encoder concatenates the query and one candidate passage and runs them through the model together, producing a relevance score for that pair. It solves the problem that independent embeddings cannot represent how a specific query relates to a specific passage. It exists as the accurate but expensive half of retrieval: accurate enough to reorder a shortlist, too slow to search a corpus with.
Technology Graph
How Cross-Encoder connects to the rest of the stack.
Alternatives
-
Bi-Encoder
concept
An alternative to Cross-Encoder · source
Comparisons
Side-by-side breakdowns with the alternatives above.