Tagged “diagnosis”
-
Which signal failed
A query returned nothing useful. A procedure for finding whether lexical missed, dense missed, fusion buried it, or the document was never indexed.
-
Why a similarity threshold doesn't travel
The cut-off that worked on your test queries fails on the next batch. What a cosine score is comparable to, and what to threshold instead.
-
When five results say the same thing
Retrieval returned five passages and one fact. Diversity at query time: per-document caps, marginal relevance, and what each one costs you.
-
A reranker cannot find what retrieval missed
Reranking reorders a candidate set and never adds to it. Why a good reranker on a shallow pipeline is money spent on the wrong stage.
-
When every document looks the same to the vector index
On a homogeneous corpus, dense scores compress and ranking becomes arbitrary. How to spot a low-contrast corpus and what still discriminates.