Enhancing language models for telecom networks using retrieval-augmented generation: A pipeline for telecom-specific QA system
Abstract
Natural Language Processing (NLP) is used to address several problems across various domains. There is an increasing demand for domain-specific NLP applications, and telecommunication networks are one of the vital fields of this application. In NLP, generative artificial intelligence (Gen-AI) has shown an excellent potential to solve many problems with its natural language understanding, comprehension, and generation capabilities. Large Language Models (LLMs) have been instrumental and one of the most integral parts of the Gen-AI applications. There are several open-source and proprietary LLMs available, where their parameter size can vary from a few billion to several trillion parameters. However, there are limitations of general-purpose pre-trained LLMs in handling domain-specific tasks, especially in the telecommunication domain. Challenges such as the interpretation of technical standards defined by organizations such as Third Generation Partnership Project (3GPP) standards, industry-specific jargon, and the need for precise technical answers necessitate specialized models and effective telecom question-answer systems. In this thesis, we present a novel Retrieval-Augmented Generation (RAG) pipeline to enhance open-source, small-size LLMs, which have less than 10 billion parameters, and finetune the model for telecom networks by leveraging RAG. This is to bridge existing gaps in domain adaptation and question-answering of 3GPP documents. The proposed RAG pipeline…
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.