Rerank-2.5 and rerank-2.5-lite: instruction-following rerankers
TL;DR – We are excited to introduce the rerank-2.5 series, which significantly improves upon rerank-2 ’s performance while also introducing instruction-following capabilities for the first time. On our standard suite of 93 retrieval datasets spanning multiple domains, rerank-2.5 and rerank-2.5-lite improve retrieval accuracy by 7.94% and 7.16% over Cohere Rerank v3.5. Furthermore, the new instruction-following feature allows users to steer the model’s output relevance scores using natural langua