NEFMind: Parameter-Efficient Fine-Tuning of Open-Source LLMs for Telecom APIs Automation

TL;DR

NEFMind employs parameter-efficient fine-tuning of open-source LLMs to streamline telecom API management, reducing communication overhead and achieving high accuracy in API call identification within 5G networks.

Contribution

It introduces a novel framework combining synthetic dataset generation, quantized low-rank adaptation, and performance evaluation for telecom API automation using open-source LLMs.

Findings

Achieves 85% reduction in communication overhead.

Attains 98-100% accuracy in API call identification.

Demonstrates comparable performance to larger models like GPT-4.

Abstract

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.