Search, retrieval & recommendation· 2020
ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
On the reading lists
- #208 in the Top 500 (2026 edition)
- #12 in Search, retrieval & recommendation (2026 edition)
Why it matters
Introduced token-level late interaction, balancing neural retrieval effectiveness with scalable search.
Condensed from the expert lists' notes.
The record
- First released
- 2020 (from arXiv 2004.12832)
- Citations
- 2,653 citations, as counted by Papers With Code (CC BY-SA 4.0)
- Named by
- both expert lists
- Score
- 0.525 · computed rank 208 · consensus 0.63, must-read 0.5, citations percentile 0.818 (2020s · retrieval), awards 0, existing lists 0. Method
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.