arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.04592cs.CLcs.CV
收藏

从静态推理到动态交互:流式大型语言模型综述

From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models

Shanghai Jiao Tong University(上海交通大学);Institute of Digital Twin, Eastern Institute of Technology(数字孪生研究院,东部技术研究院)

Junlong Tong, Zilong Wang, YuJie Ren, Peiran Yin, Hao Wu, Wei Zhang, Xiaoyu Shen

AI总结:

本文统一了流式LLM的定义,提出系统分类法,综述其方法、应用与未来方向。

摘要:

标准大型语言模型(LLM)主要设计用于预定义输入的静态推理,这限制了它们在动态实时场景中的适用性。为解决这一差距,流式LLM范式应运而生。然而,现有流式LLM的定义仍然零散,混淆了流式生成、流式输入和交互式流式架构,且缺乏系统分类法。本文对流式LLM进行了全面概述和分析。首先,我们基于数据流和动态交互建立了流式LLM的统一定义,以澄清现有歧义。基于这一定义,我们提出了当前流式LLM的系统分类法,并对其底层方法进行了深入讨论。此外,我们探讨了流式LLM在现实场景中的应用,并概述了有前景的研究方向,以支持流式智能的持续进展。我们在以下网址维护一个持续更新的相关论文仓库:此 https URL。

英文摘要:

Standard Large Language Models (LLMs) are predominantly designed for static inference with pre-defined inputs, which limits their applicability in dynamic, real-time scenarios. To address this gap, the streaming LLM paradigm has emerged. However, existing definitions of streaming LLMs remain fragmented, conflating streaming generation, streaming inputs, and interactive streaming architectures, while a systematic taxonomy is still lacking. This paper provides a comprehensive overview and analysis of streaming LLMs. First, we establish a unified definition of streaming LLMs based on data flow and dynamic interaction to clarify existing ambiguities. Building on this definition, we propose a systematic taxonomy of current streaming LLMs and conduct an in-depth discussion on their underlying methodologies. Furthermore, we explore the applications of streaming LLMs in real-world scenarios and outline promising research directions to support ongoing advances in streaming intelligence. We maintain a continuously updated repository of relevant papers at https://github.com/EIT-NLP/Awesome-Streaming-LLMs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑