Cross-encoder reranker
also: reranker · cross-encoderA model that reads query and candidate together and rescores a short list. Only reorders what the first stage already retrieved.
Our embedder and both rerankers we tested are sold as multilingual. Measured with paired Slovak and English queries, Slovak failed 55% of the time against 20%, and a cross-encoder gave three different documents the identical score.
Our unified search compared three different quantities in one column. The exact answer ranked below a weaker one, purely because of scale. What we measured, and what we changed.
Two passing evaluations in one day, both blind to the change they were meant to judge. What they missed, and the rule we took from it.
Ask our memory for a record by its own name: 93% rank-1 on plain semantic search, 43% after the biological rescore. Why a smarter score lost the easiest query, and the fix we chose.