Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Frequency Is Not Sensitivity Identifying Safety-Sensitive Experts in Sparse MoE LLM
Md Nurul Absar Siddiky, Liuwan Zhu, Yingfei Dong
Suppressing a small set of routed experts can weaken the safety behavior of a sparse Mixture-of-Experts (MoE) language model without retraining. Which experts to suppress is theref…
cs.AI2026
Safety-Oriented Routing Analysis of Mixtral MoE Under Benign and Harmful Prompts
Md Nurul Absar Siddiky
Sparse mixture-of-experts (MoE) language models activate only a small subset of parameters for each token, making router behavior a central part of model computation. This paper st…