Hybrid retrieval runs a dense search and a lexical search and has to combine two ranked lists whose scores mean completely different things: a cosine similarity of 0.83 and a BM25 score of 14.2 are not comparable, and normalising them is fragile.
Reciprocal rank fusion sidesteps the problem by throwing the scores away and using only the ranks:
You have read the opening. The rest is free with a Bezen account, and no card is needed.
Behind the sign-in