小语言模型也能内省？本文提出IFT方法，用激活引导训练小模型检测自身扰动，提升可解释性与鲁棒性。
arXiv:2607.14111v1 Announce Type: new Abstract: Can small language models detect and report on perturbations their own internal activations? We invest…
突破线性限制，LLM行为控制新范式：可逆潜在变换实现更灵活激活引导
arXiv:2606.08454v1 Announce Type: new Abstract: Activation steering provides a lightweight inference-time mechanism for controlling large language mod…
提出图正则化稀疏自编码器，提升大模型安全行为干预的精准度。
arXiv:2512.06655v3 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract activation directions for infere…