E^2Rank：你的文本嵌入亦可成为高效且经济的列表式重排器

E^2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker

October 26, 2025

作者: Qi Liu, Yanzhao Zhang, Mingxin Li, Dingkun Long, Pengjun Xie, Jiaxin Mao

cs.AI

摘要

文本嵌入模型是现实世界搜索应用中的核心组件。通过将查询和文档映射到共享的嵌入空间，它们能以较高效率实现具有竞争力的检索性能。然而，与专用重排器相比，其排序保真度仍存在局限，特别是相较于近期基于大语言模型的列表级重排器——后者能捕捉细粒度的查询-文档及文档-文档交互关系。本文提出一种简洁而有效的统一框架E^2Rank（意为高效基于嵌入的排序，亦指嵌入到排序的转换），通过基于列表级排序目标的持续训练，将单一文本嵌入模型扩展为兼具高质量检索与列表级重排能力的系统，从而在保持卓越效率的同时实现强劲的排序效果。该框架以查询与文档嵌入间的余弦相似度作为统一排序函数，通过原始查询及其候选文档构建的列表级排序提示，可视为融合了Top-K文档信号的增强型查询，类似于传统检索模型中的伪相关反馈机制。这一设计在保留基础嵌入模型效率与表征质量的同时，显著提升了其重排性能。实验表明，E^2Rank在BEIR重排基准测试中达到最先进水平，在需要深度推理的BRIGHT基准测试中展现出竞争优势，且重排延迟极低。我们还发现排序训练过程能提升模型在MTEB基准上的嵌入性能。研究结果表明，单一嵌入模型可有效统一检索与重排任务，兼具计算效率与竞争优势的排序准确性。

English

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 E^2Rank, 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, E^2Rank 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.