Steering MoE LLMs via Expert (De)Activation

11 September 2025

Papers citing "Steering MoE LLMs via Expert (De)Activation"

3 / 3 papers shown

Title
Multilingual Routing in Mixture-of-Experts Lucas Bandarkar Chenyuan Yang Mohsen Fayyaz Junlin Hu Nanyun Peng MoE 24 0 0 06 Oct 2025
ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack Yein Park Jungwoo Park Jaewoo Kang 16 0 0 30 Sep 2025
Defending MoE LLMs against Harmful Fine-Tuning via Safety Routing Alignment Jaehan Kim Minkyoo Song Seungwon Shin Sooel Son MoE 27 0 0 26 Sep 2025