Use ColBERT-style late-interaction retrieval for identifier-heavy code search instead of dense + cross-encoder rerank

RecSys Substack·medium signal

For queries dominated by function names, variable names, and other identifiers, late-interaction retrieval (ColBERT-style, storing per-token embeddings) often wins outright over the standard dense-retrieve-then-cross-encoder-rerank pipeline, delivering near cross-encoder accuracy at near bi-encoder speed. In 2026 retrieval — not generation — is the RAG bottleneck, so the retrieval primitive choice is where the accuracy is won. Actionable: benchmark a late-interaction index against your two-stage rerank pipeline specifically on symbol/identifier queries before defaulting to rerank.