English(EN) Long-Context Demonstration Selection Using State Space Models

状态空间模型提高长上下文语言模型效率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-17 04:00

研究人员开发了一种新的语言模型演示选择方法，旨在降低长上下文场景相关的计算成本。该方法利用状态空间模型（SSMs）来蒸馏Transformer模型，实现了低于0.7%的蒸馏误差。实验表明，与现有的选择方法相比，该方法可以将FLOPs降低14.2倍，并在各种文本分类和推理任务上提高6.48%的准确率。 AI

影响这项研究提供了一种显著降低长上下文语言模型计算成本的方法，可能使其得到更广泛的应用和更复杂的应用。

排序理由该集群包含一篇学术论文，详细介绍了一种提高AI模型效率的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了一种提高AI模型效率的新方法。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Ziniu Zhang, Zhenshuo Zhang, Ruoxuan Xiong, Gene Cooperman, Hongyang R. Zhang · 2026-09-17 04:00

使用状态空间模型进行长上下文演示选择

arXiv:2609.17888v1 Announce Type: cross Abstract: We study the problem of demonstration selection, which involves selecting a subset of examples for prepending to a query to a language model. This problem is closely related to in-context learning and language model inference. Sin…

本文如何被排名

报道来源 [1]

使用状态空间模型进行长上下文演示选择

相关实体

相关话题