From 443501a7a991e31afe2349b4b5b70cb60ca3a914 Mon Sep 17 00:00:00 2001 From: "Anup Kumar, PhD" Date: Tue, 21 Jul 2026 11:25:49 +0200 Subject: [PATCH] Fix typo in reranker.rst Corrected a typo in the description of the reranker model. --- docs/source/Introduction/reranker.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/Introduction/reranker.rst b/docs/source/Introduction/reranker.rst index d0da73d92..27622dae1 100644 --- a/docs/source/Introduction/reranker.rst +++ b/docs/source/Introduction/reranker.rst @@ -8,7 +8,7 @@ Reranker Reranker, or Cross-Encoder, is a model that refines the ranking of candidate pairs (e.g., query-document pairs) by jointly encoding and scoring them. Typically, we use embedder as a Bi-Encoder. It first computes the embeddings of two input sentences, then compute their similarity using metrics such as cosine similarity or Euclidean distance. -Whereas a reranker takes two sentences at the same time and directly computer a score representing their similarity. +Whereas a reranker takes two sentences at the same time and directly computes a score representing their similarity. The following figure shows their difference: