lateexp

Overview ¶

Command lateexp is an offline experiment: does late-interaction (ColBERT-style MaxSim over per-token vectors) improve paraphrastic SEED recall over the production single-vector mean-pool? It scores the WHOLE corpus by both methods (not just a re-rank of the seed set) because the hypothesis is that MaxSim catches paraphrases the single vector drops at the seed stage — a re-rank of an already-missed seed could never show that.

It does NOT change the index format or the hot path; it re-embeds the corpus at token level on the fly. Keep it to small/mid indexes (use -max-symbols / -sym-tokens to bound memory on large ones).