Maximum Similarity late interaction function introduced by ColBERT for ranking. Calculates cosine similarity between query and document token embeddings, keeping maximum score per query token for highly effective long-document retrieval.
MaxSim (Maximum Similarity) is ColBERT's late interaction similarity function that enables precise, token-level matching between queries and documents. It's particularly effective for long-document datasets.
On long-document datasets, the context-level MaxSim is by a large margin the most effective scoring function, with cross-context MaxSim as a solid second place.
Traditional dense retrieval compresses entire documents into single vectors, losing fine-grained information. MaxSim preserves token-level interactions while remaining computationally efficient.
MaxSim is used as a re-ranking stage after initial retrieval:
Late interaction ranking models deliver high-quality ranking results on large-scale datasets, which is crucial for RAG systems.
Vespa announced Long-Context ColBERT support with MaxSim in 2026, enabling efficient ColBERT search at scale.
Loading more......