analiza aiqbench
E2Rank addresses the computational bottleneck of listwise reranking by unifying retrieval and ranking tasks within a single embedding model, eliminating the need for costly autoregressive decoding. This approach maintains state-of-the-art accuracy on standard benchmarks while offering significantly lower latency than current LLM-based alternatives. The method represents a meaningful advancement in making high-fidelity search systems more efficient without sacrificing performance.
E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search
arXiv:2510.22733v3 Announce Type: replace-cross Abstract: 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.
Abstract: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.
Accepted by EMNLP 2026 main conference. Code and models are avaliable at this https URL
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
arXiv:2510.22733 [cs.CL]
(or arXiv:2510.22733v3 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2510.22733 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 241 cuvinte
Subiecte conexe
[AINews] Opus 5.5 is good at explainer videos
Latent Space · 29 sept. 2026
[AINews] The Future of Latent Space
Latent Space · 25 sept. 2026
VoiceTrace: A Benchmark and Retrieval Framework for Who-Said-What Speech Retrieval
arXiv · 17 sept. 2026
Presentation: Automating the Web With MCP: Infra That Doesn’t Break
InfoQ · 16 iun. 2026