Leveraging Uncertainty Estimation for Efficient LLM Routing

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Tuo, Mehradfar, Asal, Dimitriadis, Dimitrios, Avestimehr, Salman
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916617456189440
author Zhang, Tuo
Mehradfar, Asal
Dimitriadis, Dimitrios
Avestimehr, Salman
author_facet Zhang, Tuo
Mehradfar, Asal
Dimitriadis, Dimitrios
Avestimehr, Salman
contents Deploying large language models (LLMs) in edge-cloud environments requires an efficient routing strategy to balance cost and response quality. Traditional approaches prioritize either human-preference data or accuracy metrics from benchmark datasets as routing criteria, but these methods suffer from rigidity and subjectivity. Moreover, existing routing frameworks primarily focus on accuracy and cost, neglecting response quality from a human preference perspective. In this work, we propose the Confidence-Driven LLM Router, a novel framework that leverages uncertainty estimation to optimize routing decisions. To comprehensively assess routing performance, we evaluate both system cost efficiency and response quality. In particular, we introduce the novel use of LLM-as-a-Judge to simulate human rating preferences, providing the first systematic assessment of response quality across different routing strategies. Extensive experiments on MT-Bench, GSM8K, and MMLU demonstrate that our approach outperforms state-of-the-art routing methods, achieving superior response quality while maintaining cost efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11021
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging Uncertainty Estimation for Efficient LLM Routing
Zhang, Tuo
Mehradfar, Asal
Dimitriadis, Dimitrios
Avestimehr, Salman
Networking and Internet Architecture
Computation and Language
Deploying large language models (LLMs) in edge-cloud environments requires an efficient routing strategy to balance cost and response quality. Traditional approaches prioritize either human-preference data or accuracy metrics from benchmark datasets as routing criteria, but these methods suffer from rigidity and subjectivity. Moreover, existing routing frameworks primarily focus on accuracy and cost, neglecting response quality from a human preference perspective. In this work, we propose the Confidence-Driven LLM Router, a novel framework that leverages uncertainty estimation to optimize routing decisions. To comprehensively assess routing performance, we evaluate both system cost efficiency and response quality. In particular, we introduce the novel use of LLM-as-a-Judge to simulate human rating preferences, providing the first systematic assessment of response quality across different routing strategies. Extensive experiments on MT-Bench, GSM8K, and MMLU demonstrate that our approach outperforms state-of-the-art routing methods, achieving superior response quality while maintaining cost efficiency.
title Leveraging Uncertainty Estimation for Efficient LLM Routing
topic Networking and Internet Architecture
Computation and Language
url https://arxiv.org/abs/2502.11021