ACL 2024long8 citations

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

Ziwei Chai, Guoyin Wang, Jing Su, Tianjie Zhang, Xuanwen Huang, Xuwu Wang, Jingjing Xu, Jianbo Yuan

Abstract

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.

BibTeX
@inproceedings{chai-etal-2024-expert,
    title = "An Expert is Worth One Token: Synergizing Multiple Expert {LLM}s as Generalist via Expert Token Routing",
    author = "Chai, Ziwei  and
      Wang, Guoyin  and
      Su, Jing  and
      Zhang, Tianjie  and
      Huang, Xuanwen  and
      Wang, Xuwu  and
      Xu, Jingjing  and
      Yuan, Jianbo  and
      Yang, Hongxia  and
      Wu, Fei  and
      Yang, Yang",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.acl-long.614/",
    doi = "10.18653/v1/2024.acl-long.614",
    pages = "11385--11396"
}