SOURCE-LINKED INTELLIGENCE

Compositional Multilingual and Behavioral Attribute Steering

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

This study examines the compositionality of steering vectors for language and behavioral control in large language models. Focusing on language, jailbreak, and conciseness, we investigate whether additive, training-free composition of attribute steering vectors can preserve the intended steering effect of each attribute, across four instruction-tuned models from two model families and two size scales. We find that single-attribute steering is reliable for all three attributes, but only within an appropriate combination of intervention layer and steering strength, with abstract behaviors (jailb

Read original source ↗ Open in workspace

recordType

paper

region

Global