用轻量微调让大模型自动管理电信API，省时省力
NEFMind: Parameter-Efficient Fine-Tuning of Open-Source LLMs for Telecom APIs Automation
- 基于电信API规范生成合成数据，用低秩量化方法微调模型
- 相比人工发现，通信开销减少85%，识别准确率达98%-100%
- 小模型性能逼近GPT-4，适合部署在电信基础设施中
现代电信中的服务化架构大幅增加了网络功能（NFs）和应用接口（APIs），带来服务发现与管理的巨大复杂性。我们提出NEFMind框架，利用开源大语言模型（LLMs）的参数高效微调来应对这些挑战。该框架包含三个核心组件：从网络暴露功能（NEF）API规范生成合成数据集、通过量化低秩适配进行模型优化，以及使用GPT-4 Ref Score和BertScore评估性能。针对5G服务化架构的API，该方法相比人工发现方式实现85%的通信开销降低。基于开源Phi-2模型的实验验证表明，其在API调用识别上达到98%-100%的准确率。微调后的Phi-2模型性能接近更大规模模型如GPT-4，同时保持计算效率，适用于电信基础设施部署。研究证实了领域特定、参数高效的LLM策略在下一代电信网络复杂API生态管理中的有效性。
原文摘要 · Abstract (English)
The use of Service-Based Architecture in modern telecommunications has exponentially increased Network Functions (NFs) and Application Programming Interfaces (APIs), creating substantial operational complexities in service discovery and management. We introduce \textit{NEFMind}, a framework leveraging parameter-efficient fine-tuning of open-source Large Language Models (LLMs) to address these challenges. It integrates three core components: synthetic dataset generation from Network Exposure Function (NEF) API specifications, model optimization through Quantized-Low-Rank Adaptation, and performance evaluation via GPT-4 Ref Score and BertScore metrics. Targeting 5G Service-Based Architecture APIs, our approach achieves 85% reduction in communication overhead compared to manual discovery methods. Experimental validation using the open-source Phi-2 model demonstrates exceptional API call identification performance at 98-100% accuracy. The fine-tuned Phi-2 model delivers performance comparable to significantly larger models like GPT-4 while maintaining computational efficiency for telecommunications infrastructure deployment. These findings validate domain-specific, parameter-efficient LLM strategies for managing complex API ecosystems in next-generation telecommunications networks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。