E2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker

TL;DR

E2Rank demonstrates that a single text embedding model, trained with a listwise ranking objective, can effectively unify retrieval and reranking tasks, achieving state-of-the-art results efficiently.

Contribution

The paper introduces E2Rank, a unified framework that extends a single embedding model to perform both retrieval and reranking with high effectiveness and efficiency.

Findings

Achieves state-of-the-art reranking results on BEIR benchmark.

Demonstrates competitive performance on BRIGHT benchmark.

Improves embedding quality on MTEB benchmark through ranking training.

Abstract

Text embedding models serve as a fundamental component in real-world search applications. By mapping queries and documents into a shared embedding space, they deliver competitive retrieval performance with high efficiency. However, their ranking fidelity remains limited compared to dedicated rerankers, especially recent LLM-based listwise rerankers, which capture fine-grained query-document and document-document interactions. In this paper, we propose a simple yet effective unified framework E2Rank, means Efficient Embedding-based Ranking (also means Embedding-to-Rank), which extends a single text embedding model to perform both high-quality retrieval and listwise reranking through continued training under a listwise ranking objective, thereby achieving strong effectiveness with remarkable efficiency. By applying cosine similarity between the query and document embeddings as a unified ranking function, the listwise ranking prompt, which is constructed from the original query and its candidate documents, serves as an enhanced query enriched with signals from the top-K documents, akin to pseudo-relevance feedback (PRF) in traditional retrieval models. This design preserves the efficiency and representational quality of the base embedding model while significantly improving its reranking performance. Empirically, E2Rank achieves state-of-the-art results on the BEIR reranking benchmark and demonstrates competitive performance on the reasoning-intensive BRIGHT benchmark, with very low reranking latency. We also show that the ranking training process improves embedding performance on the MTEB benchmark. Our findings indicate that a single embedding model can effectively unify retrieval and reranking, offering both computational efficiency and competitive ranking accuracy.