// ⌕ RAG & Vector Retrieval

ColBERT (Late Interaction)

Keeps per-token vectors and matches them late for precise yet fast retrieval.

ColBERT 后期交互 2020 Advanced core

IN PLAIN WORDS

Store a vector per document token; at query time sum each query token's max similarity (MaxSim). More accurate than single vectors, much faster than cross-encoders.

Used in: High-precision retrieval and reranking

TIMELINE · prerequisites → this → what builds on it

2018 BERT2020 Dense Passage…2020 ColBERT (Late Int…

01Original paper

ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT

Omar Khattab, Matei Zaharia · 2020

arXiv ↗ ✓ Verified · arXiv API

02Where it sits

Learn the left column first; the right column builds on this one.

Learn first

ColBERT (Late Interaction)

Then you can learn

Nothing in the atlas builds on it yet

Left: prerequisites · right: builds on this · dashed: related. Full map →

03Learning resources

Official docs, explainers, courses and reference code. All links checked.

Reference code

github.com ↗EN

04Where the course teaches it

U80 Embeddings, Vector Search & Reranking BM25, sentence embeddings, DPR, ColBERT, HNSW, PQ and hybrid search. 8 h10 algorithms4 papers

On learning paths:AI Application Engineer

For AI / data

Verification: verified, checked 2026-10-21.
JSON: /api/learn/algorithms.json (id: colbert)