English(EN) SPD: Single Pass Decoding for Generative Reranking

新的SPD解码策略显著加速了LLM重排

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-01 19:30

研究人员开发了一种名为SPD（单次前向传播）的新解码策略，该策略显著加速了大型语言模型（LLM）的生成式重排。该方法在单次前向传播中解码排列中的所有序数值，将推理时间减少了64倍，同时保持了排序质量。该方法将生成式排序与组合优化联系起来，有可能实现其他实时排序机制。 AI

影响这种新的解码策略可以为基于LLM的排序系统实现实时应用。

排序理由该集群包含一篇详细介绍LLM解码新方法的论文。[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; 该集群包含一篇详细介绍LLM解码新方法的论文。[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: 43 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) · Luke Simon · 2026-09-01 19:30

SPD：生成式重排的单程解码

Large language models (LLMs) achieve state-of-the-art generative ranking quality, but the ranking they produce must be decoded, and autoregressive decoding spends one sequential forward pass per emitted token. We observe that the only tokens a ranker must emit are the $N$ ordinal…