Enhancing Large Language Models (LLMs) for Telecom using Dynamic Knowledge Graphs and Explainable Retrieval-Augmented Generation

TL;DR

This paper presents KG-RAG, a framework combining knowledge graphs and retrieval-augmented generation to improve the accuracy, reliability, and explainability of large language models in the telecom domain, addressing challenges of domain complexity and evolving standards.

Contribution

The work introduces KG-RAG, a novel integration of knowledge graphs with retrieval-augmented generation specifically designed for telecom applications, enhancing factual accuracy and reducing hallucinations.

Findings

KG-RAG outperforms LLM-only models by 21.6% in accuracy.

KG-RAG achieves 14.3% higher accuracy than standard RAG.

Experimental results demonstrate improved reliability and explainability in telecom tasks.

Abstract

Large language models (LLMs) have shown strong potential across a variety of tasks, but their application in the telecom field remains challenging due to domain complexity, evolving standards, and specialized terminology. Therefore, general-domain LLMs may struggle to provide accurate and reliable outputs in this context, leading to increased hallucinations and reduced utility in telecom operations.To address these limitations, this work introduces KG-RAG-a novel framework that integrates knowledge graphs (KGs) with retrieval-augmented generation (RAG) to enhance LLMs for telecom-specific tasks. In particular, the KG provides a structured representation of domain knowledge derived from telecom standards and technical documents, while RAG enables dynamic retrieval of relevant facts to ground the model's outputs. Such a combination improves factual accuracy, reduces hallucination, and ensures compliance with telecom specifications.Experimental results across benchmark datasets demonstrate that KG-RAG outperforms both LLM-only and standard RAG baselines, e.g., KG-RAG achieves an average accuracy improvement of 14.3% over RAG and 21.6% over LLM-only models. These results highlight KG-RAG's effectiveness in producing accurate, reliable, and explainable outputs in complex telecom scenarios.