Jul 2026
Steering Instruction Hierarchies at Inference Time
V-Steer, a training-free inference time method that restores privileged influence by editing cached value vectors at prompt positions, is introduced, a training-free inference time method that restores privileged influence by editing cached value vectors at prompt positions.
Si-Qi Zeng, Sewoong Lee, Han Zhao et al.
· arXiv.org · 2 citations