Zhi-Kun Zhang

Routing-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language Models

Experiments on WMDP and MUSE-BOOKS across multiple MoE LLMs show that TRACE consistently improves the forget-utility trade-off, yielding a 9\% relative utility improvement over the strongest baseline under comparable forgetting quality and the best performance on three out of four MUSE-BOOKS metrics.