Retrieval-Augmented Generation for Reliable Interpretation of Radio Regulations

Zakaria El Kassimi, Fares Fourati, Mohamed-Slim Alouini

Keywords: Retrieval-Augmented Generation, Large Language Models, ITU Radio Regulations, Domain-specific Question Answering

Abstract: We study question answering in the domain of radio regulations, a legally sensitive and high-stakes area. We propose a telecom-specific Retrieval-Augmented Generation (RAG) pipeline and introduce, to our knowledge, the first multiple-choice evaluation set for this domain, constructed from authoritative sources using automated filtering and human validation. To assess retrieval quality, we define a domain-specific retrieval metric, under which our retriever achieves approximately 97\% accuracy. Beyond retrieval, our approach consistently improves generation accuracy across all tested models. In particular, while naively inserting documents without structured retrieval yields only marginal gains for GPT-4o (less than 1\%), applying our pipeline results in nearly a 12\% relative improvement. These findings demonstrate that carefully targeted grounding provides a simple yet strong baseline and an effective domain-specific solution for regulatory question answering. All code and evaluation scripts, along with our derived question–answer dataset, are available at \url{https://github.com/Zakaria010/Radio-RAG}.

Submission Number: 56