Telco-oRAG: Optimizing Retrieval-augmented Generation for Telecom Queries via Hybrid Retrieval and Neural Routing

TL;DR

Telco-oRAG is a novel open-source framework that enhances telecom-specific question answering by combining domain-focused retrieval with neural routing, significantly improving accuracy and efficiency in 3GPP standards queries.

Contribution

It introduces a hybrid retrieval strategy with glossary-enhanced query refinement and neural routing, tailored for telecom domain questions, outperforming baseline models in accuracy and memory efficiency.

Findings

Up to 17.6% accuracy improvement in 3GPP questions

10.6% better lexicon query accuracy over baselines

45% reduction in memory usage with targeted retrieval

Abstract

Artificial intelligence will be one of the key pillars of the next generation of mobile networks (6G), as it is expected to provide novel added-value services and improve network performance. In this context, large language models have the potential to revolutionize the telecom landscape through intent comprehension, intelligent knowledge retrieval, coding proficiency, and cross-domain orchestration capabilities. This paper presents Telco-oRAG, an open-source Retrieval-Augmented Generation (RAG) framework optimized for answering technical questions in the telecommunications domain, with a particular focus on 3GPP standards. Telco-oRAG introduces a hybrid retrieval strategy that combines 3GPP domain-specific retrieval with web search, supported by glossary-enhanced query refinement and a neural router for memory-efficient retrieval. Our results show that Telco-oRAG improves the accuracy in answering 3GPP-related questions by up to 17.6% and achieves a 10.6% improvement in lexicon queries compared to baselines. Furthermore, Telco-oRAG reduces memory usage by 45% through targeted retrieval of relevant 3GPP series compared to baseline RAG, and enables open-source LLMs to reach GPT-4-level accuracy on telecom benchmarks.