评分 5.5 · 来源：cs.CL updates on arXiv.org · 发布于 2026-04-17
评分依据：Psychology-based steering techniques for LLMs, applies cognitive principles to model control
arXiv:2604.14463v1 Announce Type: new Abstract: Large language models (LLMs) emulate a consistent human-like behavior that can be shaped through activation-level interventions. This paradigm is converging on additive residual-stream injections, which rely on injection-strength sweeps to approximate optimal intervention settings. However, existing methods restrict the search space and sweep in uncalibrated activation-space units, potentially missing optimal intervention conditions.