E2Rank: Efficient and Effective Layer-Wise Reranking

Cesare Campagnano, Antonio Mallia, Jack Pertschuk, Fabrizio Silvestri

Abstract: Reranking models are critical to enhancing the quality of retrieval systems by refining initial search results based on query relevance. Among these, cross-encoders demonstrate higher effectiveness because of their deep semantic understanding, achieved through transformer-based architectures. However, their high computational demands pose significant challenges for real-time applications and scalability.