Yupu Gu

Machine unlearning in Mixture-of-Experts (MoE) large language models presents a critical yet underexplored challenge. Current unlearning methods applied to MoE architectures often exploit dynamic routing as an optimization shortcut: rather than genuinely erasing knowledge from expert parameters, they manipulate routers to redirect queries away from the originally assigned experts. This not only causes severe utility degradation but also leaves hazardous knowledge intact. Consequently, adversaries can bypass the router to recover sensitive information directly from dormant experts. In this study, we propose Geometric Routing Invariance Preservation (GRIP), an algorithm-agnostic framework that resolves these failure modes by enforcing hard geometric constraints on router updates. By projecting router gradient updates into the null space of the retain set's routing matrix, GRIP suppresses routing manipulation without freezing the router entirely, thereby directing the unlearning pressure into the expert parameters themselves across all relevant experts. GRIP offers two complementary variants: training-time stochastic projection and a post-training closed-form analytical correction. Extensive experiments on two MoE models across hazardous knowledge removal and copyright unlearning benchmarks demonstrate that GRIP restores routing stability from $0.21$ to $\geq 0.94$, improves retain accuracy by up to $89\%$, and reduces white-box adversarial knowledge recovery from $11\%$ to just $3\%$ while in line with dense-architecture unlearning under black-box prompt attack, establishing geometric constraints as a principled solution for genuine unlearning in sparse MoE architectures.