English(EN) Adaptive Sparsity Optimization with Learnable Soft Top-K and Per-Term Thresholding for Efficient Retrieval

新方法优化了基于LLM的检索模型的效率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 23:07

研究人员开发了一种新方法来优化神经稀疏检索模型的稀疏性，该模型利用大型语言模型（LLM）进行语义术语扩展。该方法结合了可学习软Top-K和逐项阈值等自适应策略，以及FLOPs正则化，以减小文档和查询向量的长度。使用Lion-SP模型在MS MARCO和BEIR数据集上的实验表明，在保持高相关性的同时，检索延迟和存储成本得到了显著改善。 AI

影响这项研究通过降低延迟和存储需求，有望带来更高效、更具成本效益的信息检索系统。

排序理由详细介绍一种优化神经稀疏检索模型新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.IR (Information Retrieval) 阅读 →

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; 详细介绍一种优化神经稀疏检索模型新方法的学术论文。[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: 6 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。

报道来源 [1]

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Tao Yang · 2026-10-01 23:07

面向高效检索的可学习软Top-K和逐项阈值自适应稀疏优化

Recent work on neural sparse retrieval has demonstrated strong relevance by leveraging Large Language Models (LLMs) for semantic term expansion. However, learned models paired with previous sparsification techniques still yield overly long document and query vectors partly due to…

本文如何被排名

报道来源 [1]

面向高效检索的可学习软Top-K和逐项阈值自适应稀疏优化

相关实体

相关话题