English(EN) ReuseGR: Offline--Online Decoupled Generative Retrieval via Adaptive Prefix Reuse

ReuseGR系统提升生成式检索效率和个性化水平

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-03 03:51

研究人员开发了ReuseGR，一个新颖的生成式检索系统，旨在提高效率和个性化。该系统将离线查询规划与在线个性化完成解耦，允许一个较小的模型跨相似请求复用一个较大模型的计算。这种方法显著降低了延迟，同时保持或提高了检索质量和用户参与度指标，这在离线实验和用户级别的A/B测试中得到了证明。 AI

影响该系统解耦和复用计算的方法可以显著降低检索应用中大型生成式模型的服务成本。

排序理由该条目是一篇研究论文，详细介绍了一种新的生成式检索系统。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目是一篇研究论文，详细介绍了一种新的生成式检索系统。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 8 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Ziyu Guan · 2026-11-03 03:51

ReuseGR：离线-在线解耦生成检索通过自适应前缀重用

Larger generative retrieval models can improve retrieval quality, but their decoding cost makes low-latency serving difficult. When different users submit the same query, generating complete Semantic IDs (SIDs) for every request repeats computation, while their interaction histor…