Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Zhou, Wei, Zhiqiang, Bai, Yuqi, Xiong, Xue, Wu, Jianmin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.12473
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915343587344384
author Chen, Zhou
Wei, Zhiqiang
Bai, Yuqi
Xiong, Xue
Wu, Jianmin
author_facet Chen, Zhou
Wei, Zhiqiang
Bai, Yuqi
Xiong, Xue
Wu, Jianmin
contents Model routing allocates queries to the suitable model, improving system performance while reducing costs. However, existing routing methods face practical limitations that hinder scalability in large-scale applications and struggle to keep up with the rapid growth of the large language model (LLM) ecosystem. To tackle these challenges, we propose TagRouter, a training-free model routing method designed to optimize the synergy among multiple LLMs for open-domain text generation tasks. Experimental results demonstrate that TagRouter outperforms 13 baseline methods, increasing the accept rate of system by 6.15% and reducing costs by 17.20%, achieving optimal cost-efficiency. Our findings provides the LLM community with an efficient and scalable solution for model ensembling, offering users an evolvable "super model."
format Preprint
id arxiv_https___arxiv_org_abs_2506_12473
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks
Chen, Zhou
Wei, Zhiqiang
Bai, Yuqi
Xiong, Xue
Wu, Jianmin
Computation and Language
Model routing allocates queries to the suitable model, improving system performance while reducing costs. However, existing routing methods face practical limitations that hinder scalability in large-scale applications and struggle to keep up with the rapid growth of the large language model (LLM) ecosystem. To tackle these challenges, we propose TagRouter, a training-free model routing method designed to optimize the synergy among multiple LLMs for open-domain text generation tasks. Experimental results demonstrate that TagRouter outperforms 13 baseline methods, increasing the accept rate of system by 6.15% and reducing costs by 17.20%, achieving optimal cost-efficiency. Our findings provides the LLM community with an efficient and scalable solution for model ensembling, offering users an evolvable "super model."
title TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks
topic Computation and Language
url https://arxiv.org/abs/2506.12473