@inproceedings{salim-etal-2026-expert,
    title = "Expert Calibration Lens for Pruning Mixture of Experts",
    author = "Salim, Luis Frentzen  and
      Wu, Chia-Chun  and
      Van Nhiem, Tran  and
      Ku, Lun-Wei  and
      Li, Yung-Hui",
    editor = "Durrett, Greg  and
      Jian, Ping",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-demo.72/",
    pages = "736--742",
    ISBN = "979-8-89176-392-0",
    abstract = "Expert pruning is a practical deployment technique for Mixture-of-Experts (MoE) models. It reduces resource usage and mitigates expert redundancy, but its success depends strongly on the calibration set used for pruning. In domain-general settings, it is unclear which properties of the calibration data drive good pruning outcomes, and the effects of calibration perturbations are often unintuitive. We observe, for example, that calibration sets in different languages can lead to very similar pruning results despite appearing dissimilar on the surface.To address this, we propose Expert Calibration Lens, a lightweight analysis tool that compares expert activation patterns across datasets to predict the impact of calibration perturbations without repeatedly running expensive pruning procedures. We use activations that are quick to compute and evaluate the resulting analysis for downstream task performance."
}