{"ID":2872299,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.09651","arxiv_id":"2509.09651","title":"Retrieval-Augmented Generation for Reliable Interpretation of Radio Regulations","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 https://github.com/Zakaria010/Radio-RAG.","short_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 au...","url_abs":"https://arxiv.org/abs/2509.09651","url_pdf":"https://arxiv.org/pdf/2509.09651v2","authors":"[\"Zakaria El Kassimi\",\"Fares Fourati\",\"Mohamed-Slim Alouini\"]","published":"2025-09-11T17:43:42Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\",\"cs.CL\",\"cs.LG\",\"eess.SP\"]","methods":"[\"RAG\"]","has_code":false,"code_links":[{"ID":609960,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2872299,"paper_url":"https://arxiv.org/abs/2509.09651","paper_title":"Retrieval-Augmented Generation for Reliable Interpretation of Radio Regulations","repo_url":"https://github.com/Zakaria010/Radio-RAG","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}