Enhancing Network Management Using Code Generated by Large Language Models

TL;DR

This paper presents a new approach that leverages large language models to generate task-specific code from natural language queries, improving network management by enhancing explainability, scalability, and privacy.

Contribution

It introduces a novel natural-language-based network management system using LLMs for code generation, addressing key challenges in explainability and privacy.

Findings

High accuracy in code generation for network tasks

Cost-effective approach compared to traditional methods

Potential for further improvements with program synthesis techniques

Abstract

Analyzing network topologies and communication graphs plays a crucial role in contemporary network management. However, the absence of a cohesive approach leads to a challenging learning curve, heightened errors, and inefficiencies. In this paper, we introduce a novel approach to facilitate a natural-language-based network management experience, utilizing large language models (LLMs) to generate task-specific code from natural language queries. This method tackles the challenges of explainability, scalability, and privacy by allowing network operators to inspect the generated code, eliminating the need to share network data with LLMs, and concentrating on application-specific requests combined with general program synthesis techniques. We design and evaluate a prototype system using benchmark applications, showcasing high accuracy, cost-effectiveness, and the potential for further enhancements using complementary program synthesis techniques.