explainx.ainewsletter3.5k
TrendingNewsPathwaysSkills
Pricing
explainx.ai

Upskill in AI — 16 free pathways, live workshops & bootcamps, and 50+ courses from practitioners. Plus the skills, tools, and MCP servers to practice on.

follow us

corporate training

support@explainx.ai

get started

Find your pathTake Free Evaluation

learn

pathways — start freeworkshopsbootcampscoursescertificationsmock testsexplainx universitycorporate traininglearn skills & mcp

discover

skillsmcp serversexplainx mcptoolsagentsllmsdesignsdictionaryagi trackerranks

company

aboutvisionmissionteaminstructorscommunityhackathonscareers

content

daily AI newsstate of AI — live resultsblogreleasespromptsgeneratorsresource libraryfor LLMsexplainx.ai kids

solutions

all solutionsdeveloper upskillingmarketing upskillingproduct manager upskillingleadership upskilling

newsletter · weekly

Get AI news, tools, and insights in your inbox.

supportcontactprivacytermsdata rightshow we create contentsubmission guidelines

© 2026 AISOLO Technologies Pvt Ltd

  1. Home
  2. /
  3. Dictionary
  4. /
  5. ColBERT
Retrieval & Search

ColBERT

A late-interaction retrieval model that stores per-token embeddings for documents and computes fine-grained similarity at query time, balancing bi-encoder speed with cross-encoder quality.

Ask Melo about this← all terms

ColBERT (Contextualized Late Interaction over BERT) represents each document as a set of per-token embeddings rather than a single vector. At query time, it computes a MaxSim operation — matching each query token to its closest document token — enabling fine-grained relevance scoring while still allowing document embeddings to be pre-computed and indexed. This late-interaction approach achieves cross-encoder-level quality with much better latency.

Related terms

Late Interaction RetrievalBi-EncoderCross-EncoderMulti-Vector RetrievalQuery RewritingEmbedding Model