paper-with-me

홈 › Papers

An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing

2024-03-25 · Ziwei Chai, Guoyin Wang, Jing Su, Tianjie Zhang, Xuanwen Huang, Xuwu Wang, Jingjing Xu, Jianbo Yuan, Hongxia Yang, Fei Wu, Yang Yang

We present Expert-Token-Routing, a unified generalist framework that facilitates seamless integration of multiple expert LLMs. Our framework represents expert LLMs as special expert tokens within the vocabulary of a meta LLM. The meta LLM can route to an expert LLM like generating new tokens. Expert-Token-Routing not only supports learning the implicit expertise of expert LLMs from existing instruction dataset but also allows for dynamic extension of new expert LLMs in a plug-and-play manner. It also conceals the detailed collaboration process from the user's perspective, facilitating interaction as though it were a singular LLM. Our framework outperforms various existing multi-LLM collaboration paradigms across benchmarks that incorporate six diverse expert domains, demonstrating effectiveness and robustness in building generalist LLM system via synergizing multiple expert LLMs.

📄 PDF Abstract BibTeX arXiv:2403.16854

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Synergizing Domain Expertise with Self-Awareness in Software Systems: A Patternized Architecture Guideline

2020-01-20 · Tao Chen, Rami Bahsoon, Xin Yao

To promote engineering self-aware and self-adaptive software systems in a reusable manner, architectural patterns and the related methodology provide an unified solution to handle the recurring problems in the engineerin…

Turn Waste into Worth: Rectifying Top-$k$ Router of MoE

2024-02-17 · Zhiyuan Zeng, Qipeng Guo, Zhaoye Fei, Zhangyue Yin 외

Sparse Mixture of Experts (MoE) models are popular for training large language models due to their computational efficiency. However, the commonly used top-$k$ routing mechanism suffers from redundancy computation and me…

Computational EfficiencyGPUMixture-of-Experts

METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens

2023-04-05 · CVPR 2023 1 · Zhanyu Wang, Lingqiao Liu, Lei Wang, Luping Zhou

In clinical scenarios, multi-specialist consultation could significantly benefit the diagnosis, especially for intricate cases. This inspires us to explore a "multi-expert joint diagnosis" mechanism to upgrade the existi…

Decoder

A Modular Task-oriented Dialogue System Using a Neural Mixture-of-Experts

2019-07-10 · Jiahuan Pei, Pengjie Ren, Maarten de Rijke

End-to-end Task-oriented Dialogue Systems (TDSs) have attracted a lot of attention for their superiority (e.g., in terms of global optimization) over pipeline modularized TDSs. Previous studies on end-to-end TDSs use a s…

global-optimizationMixture-of-ExpertsTask-Oriented Dialogue Systems

PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization

2026-06-02 · Ying Tang, Dong Li, Youjia Zhang, Zikai Song 외 arxiv

Unifying the complementary strengths of diverse Vision Foundation Models (VFMs) into a single efficient model is highly desirable but challenged by the negative transfer inherent in monolithic distillation. To address th…