# Late-Interaction Embeddings

> Source: https://sukruyusufkaya.com/en/glossary/late-interaction-embeddings
> Updated: 2026-05-13T20:58:21.869Z
> Type: glossary
> Category: dogal-dil-isleme
**TLDR:** A retrieval approach that matches queries and documents through token-level interaction instead of compressing each into a single vector.

<p>Late-interaction embedding methods offer a strong balance between dense retrieval efficiency and cross-encoder quality. They encode queries and documents separately, but compute final similarity through richer token-level interactions. They are especially attractive in systems that require high-quality semantic retrieval. They represent an important middle design space between efficiency and expressiveness.</p>