paper-with-me

Papers

TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks

2025-06-14 · Zhou Chen, Zhiqiang Wei, Yuqi Bai, Xue Xiong, Jianmin Wu

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."

📄 PDF Abstract BibTeX arXiv:2506.12473

Code (1)

thu-esis/jiuzhou pytorch

Tasks

Language ModelingLanguage ModellingLarge Language ModelText Generation

Similar Papers 제목 키워드 기반

List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs

2024-04-25 · An Yan, Zhengyuan Yang, Junda Wu, Wanrong Zhu 외

Set-of-Mark (SoM) Prompting unleashes the visual grounding capability of GPT-4V, by enabling the model to associate visual objects with tags inserted on the image. These tags, marked with alphanumerics, can be indexed vi…

Visual GroundingVisual Question AnsweringVisual Reasoning

SynthStrategy: Extracting and Formalizing Latent Strategic Insights from LLMs in Organic Chemistry

2025-12-01 · Daniel Armstrong, Zlatko Jončev, Andres M Bran, Philippe Schwaller arxiv

Modern computer-assisted synthesis planning (CASP) systems show promises at generating chemically valid reaction steps but struggle to incorporate strategic considerations such as convergent assembly, protecting group mi…

CacheProbe: Auditing Prompt Cache Isolation in Gateway APIs

2026-05-28 · Ryan Fahey arxiv

Over the past year, prompt caching in Large Language Models (LLMs) has become increasingly more popular across inference APIs. Prompt caching helps save precious compute resources and speeds up response times by reusing …

RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs

2025-03-08 · Zhongzhan Huang, Guoming Ling, Yupei Lin, Yandong Chen 외

Routing large language models (LLMs) is a new paradigm that uses a router to recommend the best LLM from a pool of candidates for a given input. In this paper, our comprehensive analysis with more than 8,500 LLMs reveals…

Instruction FollowingMathematical Reasoning

TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route

2025-09-17 · Hongyi Luo, Qing Cheng, Daniel Matos, Hari Krishna Gadi 외 arxiv

Humans can interpret geospatial information through natural language, while the geospatial cognition capabilities of Large Language Models (LLMs) remain underexplored. Prior research in this domain has been constrained b…