TeleMoM: Consensus-Driven Telecom Intelligence via Mixture of Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xinquan, Zhu, Fenghao, Huang, Chongwen, Yang, Zhaohui, Zhang, Zhaoyang, Muhaidat, Sami, Yuen, Chau, Debbah, Mérouane
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916771462643712
author Wang, Xinquan
Zhu, Fenghao
Huang, Chongwen
Yang, Zhaohui
Zhang, Zhaoyang
Muhaidat, Sami
Yuen, Chau
Debbah, Mérouane
author_facet Wang, Xinquan
Zhu, Fenghao
Huang, Chongwen
Yang, Zhaohui
Zhang, Zhaoyang
Muhaidat, Sami
Yuen, Chau
Debbah, Mérouane
contents Large language models (LLMs) face significant challenges in specialized domains like telecommunication (Telecom) due to technical complexity, specialized terminology, and rapidly evolving knowledge. Traditional methods, such as scaling model parameters or retraining on domain-specific corpora, are computationally expensive and yield diminishing returns, while existing approaches like retrieval-augmented generation, mixture of experts, and fine-tuning struggle with accuracy, efficiency, and coordination. To address this issue, we propose Telecom mixture of models (TeleMoM), a consensus-driven ensemble framework that integrates multiple LLMs for enhanced decision-making in Telecom. TeleMoM employs a two-stage process: proponent models generate justified responses, and an adjudicator finalizes decisions, supported by a quality-checking mechanism. This approach leverages strengths of diverse models to improve accuracy, reduce biases, and handle domain-specific complexities effectively. Evaluation results demonstrate that TeleMoM achieves a 9.7\% increase in answer accuracy, highlighting its effectiveness in Telecom applications.
format Preprint
id arxiv_https___arxiv_org_abs_2504_02712
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TeleMoM: Consensus-Driven Telecom Intelligence via Mixture of Models
Wang, Xinquan
Zhu, Fenghao
Huang, Chongwen
Yang, Zhaohui
Zhang, Zhaoyang
Muhaidat, Sami
Yuen, Chau
Debbah, Mérouane
Information Theory
Signal Processing
Large language models (LLMs) face significant challenges in specialized domains like telecommunication (Telecom) due to technical complexity, specialized terminology, and rapidly evolving knowledge. Traditional methods, such as scaling model parameters or retraining on domain-specific corpora, are computationally expensive and yield diminishing returns, while existing approaches like retrieval-augmented generation, mixture of experts, and fine-tuning struggle with accuracy, efficiency, and coordination. To address this issue, we propose Telecom mixture of models (TeleMoM), a consensus-driven ensemble framework that integrates multiple LLMs for enhanced decision-making in Telecom. TeleMoM employs a two-stage process: proponent models generate justified responses, and an adjudicator finalizes decisions, supported by a quality-checking mechanism. This approach leverages strengths of diverse models to improve accuracy, reduce biases, and handle domain-specific complexities effectively. Evaluation results demonstrate that TeleMoM achieves a 9.7\% increase in answer accuracy, highlighting its effectiveness in Telecom applications.
title TeleMoM: Consensus-Driven Telecom Intelligence via Mixture of Models
topic Information Theory
Signal Processing
url https://arxiv.org/abs/2504.02712