Before you dive in
What you’ll find in the original
- Retrieve a cheap shortlist before calling a semantic reranker.
- Compare top-1 and top-10 retrieval, not only a few convincing examples.
- Budget for one decision per query–candidate pair when scaling the shortlist.
Worth knowing
In this 40-query example, top-1 rose from 5% to 18% and top-10 from 38% to 62%; neither is a universal accuracy claim.