pith. sign in

arxiv: 2406.01768 · v1 · pith:XQEW66MUnew · submitted 2024-06-03 · 💻 cs.NI · cs.IT· eess.SP· math.IT

TSpec-LLM: An Open-source Dataset for LLM Understanding of 3GPP Specifications

classification 💻 cs.NI cs.ITeess.SPmath.IT
keywords datasettspec-llmdocumentstextitframeworkgenerationllmsopen-source
0
0 comments X
read the original abstract

Understanding telecom standards involves sorting through numerous technical documents, such as those produced by the 3rd Generation Partnership Project (3GPP), which is time-consuming and labor-intensive. While large language models (LLMs) can assist with the extensive 3GPP knowledge base, an inclusive dataset is crucial for their effective pre-training and fine-tuning. In this paper, we introduce \textit{TSpec-LLM}, an open-source comprehensive dataset covering all 3GPP documents from Release 8 to Release 19 (1999--2023). To evaluate its efficacy, we first select a representative sample of 3GPP documents, create corresponding technical questions, and assess the baseline performance of various LLMs. We then incorporate a retrieval-augmented generation (RAG) framework to enhance LLM capabilities by retrieving relevant context from the \textit{TSpec-LLM} dataset. Our evaluation shows that using a naive-RAG framework on \textit{TSpec-LLM} improves the accuracy of GPT-3.5, Gemini 1.0 Pro, and GPT-4 from 44\%, 46\%, and 51\% to 71\%, 75\%, and 72\%, respectively.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. TeleCom-Bench: How Far Are Large Language Models from Industrial Telecommunication Applications?

    cs.AI 2026-05 conditional novelty 6.0

    TeleCom-Bench reveals LLMs reach 90% on telecom intent and entity tasks but drop to 30% on solution generation and root cause analysis in live network scenarios.

  2. Multimodal Large Language Model Enabled Robust Beamforming for HAP Downlink Communications

    cs.NI 2026-04 unverdicted novelty 6.0

    A vision-language LLM forecasts HAP attitudes from telemetry for proactive beamforming, achieving 22.1% higher user service ratio and 12.5% higher sum-rate than baselines in simulations with mean latency of 36 ms.

  3. MM-Telco: Benchmarks and Multimodal Large Language Models for Telecom Applications

    cs.AI 2025-11 unverdicted novelty 6.0

    MM-Telco creates multimodal benchmarks for telecom and demonstrates that fine-tuned LLMs and VLMs achieve significant performance gains on domain-specific tasks.

  4. Against the Monolithic Wireless World Model: Why NextG Needs Composable and Agentic Intelligence

    eess.SP 2026-05 unverdicted novelty 5.0

    Wireless data lacks the self-contained tokenized substrate of text, so monolithic wireless world models are unsuitable for 6G; composable agentic systems using specialized components and explicit interfaces are the re...

  5. Against the Monolithic Wireless World Model: Why NextG Needs Composable and Agentic Intelligence

    eess.SP 2026-05 unverdicted novelty 4.0

    Argues that wireless data's configuration dependence and lack of self-containment make monolithic foundation models unsuitable for AI-native 6G, favoring instead composable agentic architectures.

  6. Customized Generative AI Agent for Transportation Engineering Practice: A Development and Continued Pre-training Guideline

    cs.AI 2026-06 unverdicted novelty 3.0

    A framework is described for adapting six LLMs to transportation engineering via LoRA-based continued pretraining on domain documents, with two models showing strongest results on BLEU-4 and ROUGE metrics.