ColBERT / late interaction
One vector per token + MaxSim matching; cross-encoder-like quality, still scalable, larger storage.
One vector per token + MaxSim matching; cross-encoder-like quality, still scalable, larger storage.
One vector per token + MaxSim matching; cross-encoder-like quality, still scalable, larger storage.
One vector per token + MaxSim matching; cross-encoder-like quality, still scalable, larger storage.