@inproceedings{manvattira-etal-2026-deepspecs,
    title = "{D}eep{S}pecs: Expert-Level Question Answering in 5{G}",
    author = "Manvattira, Aman Ganapathy  and
      Xu, Yifei  and
      Dang, Ziyue  and
      Lu, Songwu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1343/",
    pages = "26935--26953",
    ISBN = "979-8-89176-395-1",
    abstract = "5G technology enables mobile Internet access for billions of users. Its design, implementation and operations are regulated by 3GPP standard specifications. We study standard-native question answering over 5G specifications, where expert-level queries require navigating thousands of pages of cross-referenced standards that evolve across tens of releases. Existing retrieval-augmented generation (RAG) frameworks, including telecom-specific approaches, rely on semantic similarity and cannot reliably resolve cross-references or reason about specification evolution. We present DeepSpecs, a standard-native RAG system with three metadata-rich indices: SpecDB (clause-aligned specification text), ChangeDB (line-level version diffs), and TDocDB (Change Requests with design rationale). DeepSpecs resolves cross-references by recursively retrieving referenced clauses via metadata lookup, and traces evolution by mining clause changes and linking them to corresponding Change Requests. We curate two 5G QA datasets: 573 expert-annotated real-world questions and 350 evolution-focused questions derived from approved Change Requests. Across multiple LLM backends, DeepSpecs outperforms base models and state-of-the-art telecom RAG systems; ablations confirm that cross-reference resolution and evolution-aware retrieval substantially improve answer quality. Our methodology is conceptually applicable to other networked systems."
}