1
Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions
大模型引导向量新突破：不牺牲性能提示干预，IC录用论文揭示训练原则。
arXiv:2605.05983v2 Announce Type: replace Abstract: Recently, steering vectors (SVs) have emerged as an effective and lightweight approach to steer be…