Tag: late-interaction

All the articles with the tag "late-interaction".

• Reranking and Late Interaction: Cross-Encoders to ColBERT

  Updated:19 Oct, 2026

  Retrieval has to be cheap per document because it scores every document; reranking can be expensive per document because it only sees the top few. The bi-encoder and cross-encoder, their cost per query computed, ColBERT's late interaction and MaxSim worked token by token, why max and not mean, hard negatives, index sizes with ColBERTv2's compression, and LLM rerankers. Then cross-encoder reranking measured on the English and Vietnamese benchmark of Semantic and Hybrid Search, with what it gains and what it costs.