Balancing Information Accuracy and Response Timeliness in Networked LLMs

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Turkmen, Yigit, Buyukates, Baturalp, Bastopcu, Melih
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909720634195968
author Turkmen, Yigit
Buyukates, Baturalp
Bastopcu, Melih
author_facet Turkmen, Yigit
Buyukates, Baturalp
Bastopcu, Melih
contents Recent advancements in Large Language Models (LLMs) have transformed many fields including scientific discovery, content generation, biomedical text mining, and educational technology. However, the substantial requirements for training data, computational resources, and energy consumption pose significant challenges for their practical deployment. A promising alternative is to leverage smaller, specialized language models and aggregate their outputs to improve overall response quality. In this work, we investigate a networked LLM system composed of multiple users, a central task processor, and clusters of topic-specialized LLMs. Each user submits categorical binary (true/false) queries, which are routed by the task processor to a selected cluster of $m$ LLMs. After gathering individual responses, the processor returns a final aggregated answer to the user. We characterize both the information accuracy and response timeliness in this setting, and formulate a joint optimization problem to balance these two competing objectives. Our extensive simulations demonstrate that the aggregated responses consistently achieve higher accuracy than those of individual LLMs. Notably, this improvement is more significant when the participating LLMs exhibit similar standalone performance.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02209
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Balancing Information Accuracy and Response Timeliness in Networked LLMs
Turkmen, Yigit
Buyukates, Baturalp
Bastopcu, Melih
Machine Learning
Artificial Intelligence
Information Theory
Networking and Internet Architecture
Recent advancements in Large Language Models (LLMs) have transformed many fields including scientific discovery, content generation, biomedical text mining, and educational technology. However, the substantial requirements for training data, computational resources, and energy consumption pose significant challenges for their practical deployment. A promising alternative is to leverage smaller, specialized language models and aggregate their outputs to improve overall response quality. In this work, we investigate a networked LLM system composed of multiple users, a central task processor, and clusters of topic-specialized LLMs. Each user submits categorical binary (true/false) queries, which are routed by the task processor to a selected cluster of $m$ LLMs. After gathering individual responses, the processor returns a final aggregated answer to the user. We characterize both the information accuracy and response timeliness in this setting, and formulate a joint optimization problem to balance these two competing objectives. Our extensive simulations demonstrate that the aggregated responses consistently achieve higher accuracy than those of individual LLMs. Notably, this improvement is more significant when the participating LLMs exhibit similar standalone performance.
title Balancing Information Accuracy and Response Timeliness in Networked LLMs
topic Machine Learning
Artificial Intelligence
Information Theory
Networking and Internet Architecture
url https://arxiv.org/abs/2508.02209