LLM-Augmented Knowledge Base Construction for Root Cause Analysis

doi:10.1109/ACCESS.2026.3658655

LLM-Augmented Knowledge Base Construction for Root Cause Analysis

2026-01-28

0

OA

AI

Oscar Escamilla Delgado

DOI：10.1109/ACCESS.2026.3658655

Original

Save

View PDF

Abstract

En 中文

Communications networks now form the backbone of our digital world, with fast and reliable connectivity. However, even with appropriate redundancy and failover mechanisms, it is difficult to guarantee “five 9s” (99.999%) reliability, requiring rapid and accurate root cause analysis (RCA) during outages. In the event of an outage, rapid and accurate RCA becomes essential to restore service and prevent future disruptions. This study evaluates three Large Language Model (LLM) methodologies — Fine-Tuning, RAG, and a Hybrid approach — for constructing a Root Cause Analysis (RCA) Knowledge Base from support tickets. We compare their performance using a comprehensive suite of lexical and semantic similarity metrics. Our experiments on a real industrial dataset demonstrate that the generated knowledge base provides an excellent starting point for accelerating RCA tasks and improving network resilience.

Keywords:

Association rules mining

communication networks

large language models (LLMs)

knowledge base construction

root cause analysis (RCA)

service assurance (SA)

retrieval-augmented generation (RAG)

LLM-Augmented Knowledge Base Construction for Root Cause Analysis

Abstract

AI Summary

Journal

Organization