arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.00715cs.AIcs.NIstat.ME
收藏

基于意图漂移引导的大语言模型意图保障

Intent Assurance using LLMs guided by Intent Drift

University of Toronto(多伦多大学)

Kristina Dzeparoska, Ali Tizghadam, Alberto Leon-Garcia

AI总结:

本文提出一种基于大语言模型生成AI驱动策略的意图保障框架,用于检测意图漂移并采取行动,确保意图在动态网络中持续实现。

摘要:

意图驱动网络(IBN)为网络管理带来了范式转变,它有望以自动化方式将意图和业务目标与网络运营对齐。然而,其实际实现面临挑战:1)处理意图,即翻译、分解并识别实现意图的逻辑;2)意图一致性,即考虑到动态网络,逻辑应充分调整以保障意图。为解决后者,意图保障的任务是持续验证和确认,包括采取必要行动使运营状态与目标状态对齐。在本文中,我们定义了一个保障框架,使我们能够在意图漂移发生时检测并采取行动。为此,我们利用由大语言模型(LLMs)生成的AI驱动策略,这些模型能够快速学习必要的上下文内需求,并协助意图的实现与保障。

英文摘要:

Intent-Based Networking (IBN) presents a paradigm shift for network management, by promising to align intents and business objectives with network operations--in an automated manner. However, its practical realization is challenging: 1) processing intents, i.e., translate, decompose and identify the logic to fulfill the intent, and 2) intent conformance, that is, considering dynamic networks, the logic should be adequately adapted to assure intents. To address the latter, intent assurance is tasked with continuous verification and validation, including taking the necessary actions to align the operational and target states. In this paper, we define an assurance framework that allows us to detect and act when intent drift occurs. To do so, we leverage AI-driven policies, generated by Large Language Models (LLMs) which can quickly learn the necessary in-context requirements, and assist with the fulfillment and assurance of intents.

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。

↑