Story
arxiv_cs_cl · Nov 2, 2026 · paper
Source brief
VIAS: Value-Isolating Activation Steering for Multi-Value Alignment and Compliance for Organisations
arxiv.orgNov 2, 2026
original source linked
In brief
Organisations increasingly deploy large language model agents that must follow organisational values. We check whether activation steering, which adds vectors to a model's internal activations during generation withou...
Feed lens
agenteval