MoE 模型剪枝的常用假设被实验证伪了——做模型压缩或可解释性研究的团队，建议重新审视你的专家选择策略，别再依赖路由统计指标。
这篇论文对混合专家模型（MoE）中的专家重要性评估方法进行了因果审计。研究者发现，当前广泛使用的路由统计指标（如利用率、激活范数、路由权重分布）无法预测哪些专家可以被移除而不影响模型功能。他们在 OLMoE-1B-7B-0924、Qwen1.5-MoE-A2.7B 和 DeepSeek-V2-Lite 三个高冗余 MoE 架构上进行了 token 级干预实验，结果在所有 60 个指标-层组合中，观测指标与因果重要性之间的效应量均低于 Cohen's d = 0.17。现有剪枝方法之所以有效，并非因为它们识别出了可去除的专家，而是因为早期层的冗余性使得大多数选择标准可以互换。这项研究为可解释性领域提供了一个明确的反例，说明从总体观测统计到 token 级干预结论的推理步骤需要更严格的因果验证。
From Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts Models
Interpretability methods routinely use population-level summary statistics over observed model behaviour to license claims about the effects of targeted interventions on specific computations; in Pearl's terms, they treat rung-1 associational evidence as if it supported rung-2 interventional conclusions, a move whose validity is rarely tested. We examine one concrete instance: the use of routing statistics in Mixture-of-Experts (MoE) pruning, where utilization rates, activation norms, and routing weight distributions are treated as predictors of which experts can be removed without functional cost. A token-level interventional audit across three high-redundancy MoE architectures (OLMoE-1B-7B-0924, Qwen1.5-MoE-A2.7B, DeepSeek-V2-Lite) finds no observational metric predicts causal expert importance after multiple-comparison correction in any model, with effect sizes below Cohen's $d = 0.17$ across all 60 metric-layer combinations. A per-token routing weight control rules out insufficient power, recovering a single Bonferroni-significant signal at OLMoE's final MoE layer ($d = +0.231$, $p = 0.0013$). Existing pruning methods succeed in this regime not by identifying dispensable experts but because early-layer redundancy renders most selection criteria interchangeable. Our results provide an explicit counterexample to the common inferential step from population-level observational summaries to token-level interventional claims about expert importance, and illustrate how interventional audits can calibrate the evidential standards for interpretability claims.