@inproceedings{wang-etal-2026-illusion,
    title = "The Illusion of Specialization: Unveiling the Domain-Invariant ``Standing Committee'' in Mixture-of-Experts Models",
    author = "Wang, Yan  and
      Xu, Yitao  and
      Shen, Nanhan  and
      Su, Jinyan  and
      Huang, Jimin  and
      Zhu, Zining",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.665/",
    pages = "14601--14618",
    ISBN = "979-8-89176-390-6",
    abstract = "Mixture of Experts models are widely assumed to achieve domain specialization through sparse routing. In this work, we question this assumption by introducing COMMITTEEAUDIT, a post hoc framework that analyzes routing behavior at the level of expert groups rather than individual experts. Across three representative models and the MMLU benchmark, we uncover a domain invariant Standing Committee. This is a compact coalition of routed experts that consistently captures the majority of routing mass across domains, layers, and routing budgets, even when architectures already include shared experts. Qualitative analysis further shows that Standing Committees anchor reasoning structure and syntax, while peripheral experts handle domain-specific knowledge. These findings reveal a strong structural bias toward centralized computation, suggesting that specialization in Mixture of Experts models is far less pervasive than commonly believed. Crucially, this inherent bias indicates that current training objectives, such as load-balancing losses that enforce uniform expert utilization, may be working against the model{'}s natural optimization path, thereby limiting training efficiency and performance."
}