用单一模型同时实现高效检索与精准排序，速度远超传统大模型重排。
E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search
- 将列表级重排目标引入嵌入模型，通过伪相关反馈机制实现无自回归重排。
- 在BEIR上达最优效果，推理延迟仅为现有LLM重排器的1/10。
- 单模型兼具检索与重排能力，适合需要低延迟高精度的搜索系统。
文本嵌入模型在检索中表现优异且效率高，但其排序精度不及基于大语言模型的列表级重排器，后者虽能捕捉细粒度查询-文档和文档-文档交互，却计算成本高昂。我们提出E2Rank（高效嵌入式排序），一个统一框架，通过在列表级排序目标下对单一文本嵌入模型进行持续训练，使其同时支持检索与列表级重排。核心思想是将由查询及其前K个候选构成的列表级提示视为伪相关反馈（PRF）查询，利用余弦相似度对预计算文档嵌入进行重排，无需自回归解码。实验表明，E2Rank在BEIR上达到顶尖性能，在推理密集型BRIGHT基准上表现相当，显著低于现有LLM重排器的延迟，并在MTEB上提升了嵌入性能——所有成果均来自单一模型。
原文摘要 · Abstract (English)
Text embedding models deliver competitive retrieval performance with high efficiency, but their ranking fidelity remains limited compared to LLM-based listwise rerankers, which capture fine-grained query-document and document-document interactions at high computational cost. We propose E2Rank (Efficient Embedding-based Ranking), a unified framework that extends a single text embedding model to perform both retrieval and listwise reranking via continued training under a listwise ranking objective. The key insight is to treat the listwise prompt---constructed from the query and its top-K candidates---as a pseudo-relevance feedback (PRF) query, enabling reranking via cosine similarity against precomputed document embeddings without autoregressive decoding. Empirically, E2Rank achieves state-of-the-art results on BEIR, competitive performance on the reasoning-intensive BRIGHT benchmark, significantly lower latency than existing LLM-based rerankers, and improved embedding performance on MTEB---all within a single model.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。