mlsanityData to 14 Oct 2026

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

arXiv 2505.11856 ↗First posted 17 May 2025cs.IRcited by 3

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 26 of its 36 references that are in the map. First posted on arXiv 17 May 2025.

Builds on

26 of 36 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors5 Apr

Other references · 25

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  5. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  6. 2017Billion-scale similarity search with GPUscited by 2,497
  7. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  8. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  9. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
  10. 2023Instruction Tuning for Large Language Models: A Surveycited by 623
  11. 2021Compacter: Efficient Low-Rank Hypercomplex Adapter Layerscited by 460
  12. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
13 more
  1. 2022Matryoshka Representation Learningcited by 282
  2. 2023How is ChatGPT's behavior changing over time?cited by 270
  3. 2020The Computational Limits of Deep Learningcited by 193
  4. 2018Neural Approaches to Conversational AIcited by 165
  5. 2023Unleashing the potential of prompt engineering for large language modelscited by 72
  6. 2020Domain-specific Knowledge Graphs: A surveycited by 68
  7. 2023TeleQnA: A Benchmark Dataset to Assess Large Language Models Telecommunications Knowledgecited by 63
  8. 2024TelecomGPT: A Framework to Build Telecom-Specfic Large Language Modelscited by 40
  9. 2024Telco-RAG: Navigating the Challenges of Retrieval-Augmented Language Models for Telecommunicationscited by 26
  10. 2024Tele-LLMs: A Series of Specialized Large Language Models for Telecommunicationscited by 25
  11. 2024TelecomRAG: Taming Telecom Standards with Retrieval Augmented Generation and LLMscited by 13
  12. 2024Telecom Language Models: Must They Be Large?cited by 10
  13. 2025Chat3GPP: An Open-Source Retrieval-Augmented Generation Framework for 3GPP Documentscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025TeleTables: A Benchmark for Large Language Models in Telecom Table Interpretationcited by 6
  2. 2026TelecomGPT-R1: Unified Post-Training for Reasoning Across Heterogeneous Telecom Taskscited by 1
  3. 2025DeepSpecs: Expert-Level Questions Answering in 5Gcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network
  2. 2025Benchmarking Vector, Graph and Hybrid Retrieval Augmented Generation (RAG) Pipelines for Open Radio Access Networks (ORAN)
  3. 2026ARMOR: Adaptive Retriever Optimization for Low-Resource Telecom Question Answering
  4. 2025How to Discover Knowledge for FutureG: Contextual RAG and LLM Prompting for O-RAN
  5. 2025TelcoAI: Advancing 3GPP Technical Specification Search through Agentic Multi-Modal Retrieval-Augmented Generation
  6. 2025Enhancing Large Language Models (LLMs) for Telecommunications using Knowledge Graphs and Retrieval-Augmented Generation
  7. 2024QMOS: Enhancing LLMs for Telecommunication with Question Masked loss and Option Shuffling
  8. 2024Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards