Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering

arXiv:2610.19359v1 Announce Type: cross Abstract: Activation steering adds a vector to a model's hidden states to control a named behaviour. A gain on that behaviour, however, does not show that the vector controls it directly: it may act through a component shared with neighbouring behaviours, which unsteered and random baselines cannot separate. We introduce the competing-target test: a vector is compared with the vector built the same way for a competing target, and an equivalence test states when their difference is below a useful margin. We apply it in open-weight models to vectors for Kantian deontology, which judges an act by the rule it follows, and act utilitarianism, which judges it by the welfare it produces. On held-out situations, prompting a framework raises its score and lowers the other's, whereas vectors for either framework move both scores alike, and none reaches the margin. The two vectors share most of their direction, a request to apply some framework; the same construction separates an optimistic from a pessimistic tone, whose vectors share much less. What a vector shares with its competitors therefore sets what it controls: steering a perspective can deliver a mixture, and measuring a disposition can measure its neighbours, unless tested against the competing target.

Related

• What Does Activation Steering Control? Attribution Across Answer Encodings and Output-Sensitive Subspaces
• Spherical Steering: Geometry-Aware Activation Rotation for Language Models
• Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control
• Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy
• Empathy Is Steerable but Multi-Axial: Mechanism Geometry and Persona Effects in LLMs

Source: arXiv cs.CL | 2026-10-15