Lune

ACL Findings2026

DeepSpecs: Expert-Level Question Answering in 5G

Aman Ganapathy Manvattira, Yifei Xu, Ziyue Dang, Songwu Lu

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 DEEP-SPECS, a standard-native RAG system with three metadata-rich indices: SpecDB (clausealigned specification text), ChangeDB (linelevel 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions cites Retrieval Augmented Language Model Pre-Training
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on4

  1. Retrieval Augmented Language Model Pre-TrainingKelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat et al.ICML 2020 · 2,937 citations
  2. Precise Zero-Shot Dense Retrieval without Relevance LabelsLuyu Gao, Xueguang Ma, Jimmy Lin, Jamie CallanACL 2023 · 211 citations
  3. Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step QuestionsHarsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish SabharwalACL 2023 · 187 citations
  4. Seeing the Forest for the Trees: Understanding Security Hazards in the 3GPP Ecosystem through Intelligent Analysis on Change RequestsYi Chen, Di Tang, Yepeng Yao, Mingming Zha et al.USENIX Security 2022

Related papers

  1. AutoEvolve: Automatically Evolving Queries for Applicable and Scalable Retrieval-Augmented Generation BenchmarkingDingchu Zhang, Xiaowen Zhang, Yue Fei, Renjun Hu et al.EMNLP Findings 2025
  2. T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge RetrievalDong Li, Yichen Niu, Ying Ai, Xiang Zou et al.ACM MM 2025 · 11 citations
  3. DeepNote: Note-Centric Deep Retrieval-Augmented GenerationRuobing Wang, Qingfei Zhao, Yukun Yan, Daren Zha et al.EMNLP Findings 2025 · 2 citations
  4. EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic RetrievalJiashi Lin, Changhong Jiang, Xiangru Lin, Ruifei Zhang et al.CVPR 2026 · 2 citations
  5. Synthetic Multimodal Question GenerationIan Wu, Sravan Jayanthi, Vijay Viswanathan, Simon Rosenberg et al.EMNLP Findings 2024 · 5 citations
Dusk over the sea between two cliffs drawn in fine vertical lines