Cross-Encoder achieve higher performance than Bi-Encoders, however, they do not scale well for large datasets. Here, it can make sense to combine Cross- and Bi-Encoders, for example, in [[Information Retrieval (IR) System]] / [[Semantic Search]] scenarios, for [[Hybrid Search]]: 1. First, you use an efficient Bi-Encoder to retrieve e.g. the top-100 most similar sentences for a query. 2. Then, you use a Cross-Encoder to re-rank these 100 hits by computing the score for every (query, hit) combination. ![[Pasted image 20240803142915.png]] https://www.sbert.net/examples/applications/cross-encoder/README.html#combining-bi-and-cross-encoders