arXiv cs.CL
· Papers
Steering the Language Axis: From Linear Decodability to Causal Control
arXiv:2608.12334v1 Announce Type: new Abstract: Despite the impressive multilingual capabilities of Large Language Models, the latent dynamics dictating language selection remain poorly understood. In this work, we ask whether language identity is merely linearly decodable from hidden states, or if it can be causally c