arXiv:2510.08734v3 Announce Type: replace Abstract: A growing body of research has demonstrated that the behavior of large language models can be effectively controlled at inference time by directly modifying their internal states, either through vector additions to their activations or through updates to their weight matrices. These techniques, while powerful, are often guided by empirical heuristics, such as deriving ``steering vectors'' from the average activations of contrastive prompts. Building on the foundational work of Dherin et al. (2025), who discovered that a prompt's influence mat
Source: arXiv cs.LG — read the full report at the original publisher.