slowbench
RetrievalInferenceEvalsAgentsSeriesArchive

Three runs, one boundary

What reranking can and cannot do

A reranker reorders a list someone else built. That single fact decides which problems it can touch and which it cannot, and it is the difference between a week well spent and a week spent swapping models that could never have helped. These three posts find the boundary, then find out why the reranker inside it was failing anyway.

2 posts

  1. 1
    Retrieval9 min

    Reranking cannot find what retrieval missed

    I swapped four rerankers and watched Pass@1 climb while recall sat at exactly 47.6% every single time.

  2. 2
    Retrieval10 min

    Your reranker speaks English. Your tickets do not.

    Turning on the default reranker made search worse. The model name had a two-letter suffix I had never looked at.