DeepSpecs: Expert-Level Questions Answering in 5G

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Manvattira, Aman Ganapathy, Xu, Yifei, Dang, Ziyue, Lu, Songwu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911247042084864
author Manvattira, Aman Ganapathy
Xu, Yifei
Dang, Ziyue
Lu, Songwu
author_facet Manvattira, Aman Ganapathy
Xu, Yifei
Dang, Ziyue
Lu, Songwu
contents 5G technology enables mobile Internet access for billions of users. Answering expert-level questions about 5G specifications requires navigating thousands of pages of cross-referenced standards that evolve across 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 RAG system enhanced by structural and temporal reasoning via three metadata-rich databases: SpecDB (clause-aligned specification text), ChangeDB (line-level version diffs), and TDocDB (standardization meeting documents). DeepSpecs explicitly resolves cross-references by recursively retrieving referenced clauses through metadata lookup, and traces specification evolution by mining changes and linking them to Change Requests that document design rationale. We curate two 5G QA datasets: 573 expert-annotated real-world questions from practitioner forums and educational resources, 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 explicit cross-reference resolution and evolution-aware retrieval substantially improve answer quality, underscoring the value of modeling the structural and temporal properties of 5G standards.
format Preprint
id arxiv_https___arxiv_org_abs_2511_01305
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeepSpecs: Expert-Level Questions Answering in 5G
Manvattira, Aman Ganapathy
Xu, Yifei
Dang, Ziyue
Lu, Songwu
Computation and Language
Artificial Intelligence
Networking and Internet Architecture
5G technology enables mobile Internet access for billions of users. Answering expert-level questions about 5G specifications requires navigating thousands of pages of cross-referenced standards that evolve across 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 RAG system enhanced by structural and temporal reasoning via three metadata-rich databases: SpecDB (clause-aligned specification text), ChangeDB (line-level version diffs), and TDocDB (standardization meeting documents). DeepSpecs explicitly resolves cross-references by recursively retrieving referenced clauses through metadata lookup, and traces specification evolution by mining changes and linking them to Change Requests that document design rationale. We curate two 5G QA datasets: 573 expert-annotated real-world questions from practitioner forums and educational resources, 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 explicit cross-reference resolution and evolution-aware retrieval substantially improve answer quality, underscoring the value of modeling the structural and temporal properties of 5G standards.
title DeepSpecs: Expert-Level Questions Answering in 5G
topic Computation and Language
Artificial Intelligence
Networking and Internet Architecture
url https://arxiv.org/abs/2511.01305