RASET: Router-Agnostic Safety-Critical Expert Tuning Exposes Localized Safety Enforcement Failures in Mixture-of-Experts LLMs
Mixture-of-Experts (MoE) LLMs rely on sparse, router-driven expert activation, yet how safety alignment interacts with routed expert specialization remains underexplored. A common intuition is that safety behavior may be controlled by routing harmful requests to distinct refusal-oriented experts. In this work, we provide empirical evidence for a different picture: routing patterns in aligned MoE LLMs are largely topic-driven, while safety behavior can be altered with little change to the model's intrinsic routing path. Motivated by this observation, we present RASET (Router-Agnostic Safety-Critical Expert Tuning), a red-teaming framework that probes safety enforcement that is localized in...
| Authors | Zhibo Zhang, Yuxi Li, Zhen Ouyang et al. |
|---|---|
| Primary category | cs.CL |
| Published | 28 May 2026 |
| Last updated at source | 23 August 2026 |
Connected in the knowledge graph
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.