Re:You Don't Need Re-Ranking: Understanding the Superlinked ...
by _QrE on Friday May 23, 2025 @02:59PM
(#44075495)
I don't mean to imply that it's a solved problem; all I'm saying is that in a lot of cases, the "weak initial retrieval" assertion stated by the article is not true. And if you can get a long way using what has now become the industry standard, there's not really a case to be made that BM25 is bad/unsuited, unless the improvement you gain from something more complex is more than just marginal.
Re:You Don't Need Re-Ranking: Understanding the Superlinked ...
by supo on Saturday May 24, 2025 @12:21PM
(#44082053)
one thing to remember is that bm25 is purely in the domain of text - the moment any other signal enters in the picture (and it ~always does in sufficiently important systems), bm25 alone can literally have 0 recall.
Treating BM25 as a silver bullet is just as strange as treating vector search as the "true way" to solve retrieval.