English(EN) Mapping Text to Multiplex Graph: Prompt Compression as L\'evy Walk-Guided Graph Pruning

新的RAGP方法使用图剪枝和莱维行走来压缩提示

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-03 04:00

研究人员开发了一种新颖的提示压缩技术，称为RAGP，它将文本建模为多重图，以捕捉局部句法和全局语义关系。该方法利用莱维行走来有效地识别和修剪图结构中的冗余信息。在LongBench基准测试上的实验表明，RAGP在更高的压缩率下，平均得分高于LongLLMLingua等现有方法。 AI

影响这项研究可能导致LLM更有效地处理长文本输入，提高性能并降低计算成本。

排序理由该集群描述了一篇详细介绍AI模型中提示压缩新方法的学术论文。[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; 该集群描述了一篇详细介绍AI模型中提示压缩新方法的学术论文。[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: 91 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.AI TIER_1 English(EN) · Yaxin Gao, Yao Lu, Jinhong Deng, Jiaqi Nie, Zhe Tang, Jian Zhang, Zhaowei Zhu, Shanqing Yu, Qi Xuan, Joey Tianyi Zhou · 2026-07-03 04:00

将文本映射到多路图：以莱维游走引导的图剪枝作为提示压缩

arXiv:2607.01241v1 Announce Type: cross Abstract: Existing prompt compression methods treat text as flat token sequences, failing to capture the distributed nature of important information, which is often spread across multiple locations and connected through both local syntactic…