Pith. sign in

REVIEW 9 cited by

TelecomGPT: A Framework to Build Telecom-Specfic Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.09424 v1 pith:6QYN4KXG submitted 2024-07-12 eess.SP cs.AI

classification eess.SPcs.AI
keywords telecomllmsbenchmarksevaluationcodedatasetdomaingeneration
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) have the potential to revolutionize the Sixth Generation (6G) communication networks. However, current mainstream LLMs generally lack the specialized knowledge in telecom domain. In this paper, for the first time, we propose a pipeline to adapt any general purpose LLMs to a telecom-specific LLMs. We collect and build telecom-specific pre-train dataset, instruction dataset, preference dataset to perform continual pre-training, instruct tuning and alignment tuning respectively. Besides, due to the lack of widely accepted evaluation benchmarks in telecom domain, we extend existing evaluation benchmarks and proposed three new benchmarks, namely, Telecom Math Modeling, Telecom Open QnA and Telecom Code Tasks. These new benchmarks provide a holistic evaluation of the capabilities of LLMs including math modeling, Open-Ended question answering, code generation, infilling, summarization and analysis in telecom domain. Our fine-tuned LLM TelecomGPT outperforms state of the art (SOTA) LLMs including GPT-4, Llama-3 and Mistral in Telecom Math Modeling benchmark significantly and achieve comparable performance in various evaluation benchmarks such as TeleQnA, 3GPP technical documents classification, telecom code summary and generation and infilling.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

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

  1. FlexNGIA 2.0: Redesigning the Internet with Agentic AI -- Protocols, Services, and Traffic Engineering Designed, Deployed, and Managed by AI

    cs.NI 2025-09 conditional novelty 6.0 of 10

    LLM-based agents can autonomously generate working custom transport protocols, congestion-control kernel modules, and resource-allocation weight updates in emulated proof-of-concept experiments.

  2. TeleMath: A Benchmark for Large Language Models in Telecom Mathematical Problem Solving

    cs.AI 2025-06 conditional novelty 6.0 of 10

    TeleMath introduces 500 numerical telecom math problems and shows reasoning-optimized LLMs outperform larger general-purpose models on them.

  3. WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless Communications

    cs.CL 2025-05 conditional novelty 6.0 of 10

    WirelessMathBench, a 587-question benchmark drawn from 40 wireless communications papers, finds that leading LLMs score only 38.05% on average and 7.83% on full equation completion, revealing weak symbolic derivation ability.

  4. Metaverse Framework for Wireless Systems Management

    cs.NI 2025-08 unverdicted novelty 4.0 of 10

    A proposed metaverse-based architecture aims to simulate, visualize, and optimize wireless networks by combining XR, digital twins, AI, IoT, blockchain, and 6G connectivity.

  5. Benchmarking Vector, Graph and Hybrid Retrieval Augmented Generation (RAG) Pipelines for Open Radio Access Networks (ORAN)

    cs.AI 2025-07 conditional novelty 4.0 of 10

    On a 600-question subset of ORAN-Bench-13K, GraphRAG and Hybrid GraphRAG beat plain vector RAG on factual accuracy, but Hybrid GraphRAG scored below vector RAG on context relevance.

  6. On the Convergence of Large Language Model Optimizer for Black-Box Network Management

    cs.IT 2025-07 reject novelty 4.0 of 10

    The paper claims a first convergence proof for LLM-based black-box optimizers, but the key lemma is proven by assertion rather than derivation.

  7. Foundation Model Empowered Synesthesia of Machines (SoM): AI-native Intelligent Multi-Modal Sensing-Communication Integration

    eess.SP 2025-06 conditional novelty 4.0 of 10

    The paper proposes a systematic classification and two roadmaps for using foundation models (LLMs and wireless foundation models) to design Synesthesia of Machines systems for 6G, with preliminary case-study evidence ...

  8. Large Language Models-Empowered Wireless Networks: Fundamentals, Architecture, and Challenges

    cs.NI 2025-06 conditional novelty 3.0 of 10

    A magazine-style position paper that frames LLM-native wireless systems and illustrates a modified DDQN scheme that appears to improve convergence over plain DDQN in simulation.

  9. From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications

    cs.AI 2025-05 conditional novelty 2.0 of 10

    This paper is a broad tutorial on applying LAMs and agentic AI to 6G, largely restating existing research rather than introducing new results.

Pith tools