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

2025-05-17

AI Summary

To address low accuracy and high memory overhead in 3GPP standard question answering for telecom intelligent services, this paper proposes a lightweight, open-source RAG framework tailored for 6G. Methodologically, it introduces the first domain-specific hybrid retrieval paradigm for telecommunications—jointly leveraging official 3GPP documentation and web search results; designs a dictionary-enhanced query refinement mechanism to improve technical term understanding; and incorporates a lightweight neural router for dynamic retrieval path selection. The framework is fully compatible with open-source LLMs and features an optimized RAG pipeline. Key contributions include: (1) the first efficient, 3GPP-specialized QA framework; (2) significant improvements in technical QA accuracy (+17.6%) and terminology query performance (+10.6%); and (3) a 45% reduction in memory footprint. The open-sourced model achieves GPT-4–level performance on telecom-specific benchmarks.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Question Answering

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Optimizing RAG for telecom queries via hybrid retrieval
• Improving accuracy in answering 3GPP-related technical questions
• Reducing memory usage in telecom domain retrieval systems

Innovation

• Hybrid retrieval combines 3GPP and web search
• Neural router enables memory-efficient retrieval
• Glossary-enhanced query refinement improves accuracy