← Back ◬ AI & Machine Learning —

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency

arXiv AI Archived Mar 16, 2026 ✓ Full text saved

arXiv:2603.12298v1 Announce Type: cross Abstract: Activation engineering enables precise control over Large Language Models (LLMs) without the computational cost of fine-tuning. However, existing methods deriving vectors from static activation differences are susceptible to high-dimensional noise and layer-wise semantic drift, often capturing spurious correlations rather than the target intent. To address this, we propose Global Evolutionary Refined Steering (GER-steer), a training-free framewor

Full text archived locally

✦ AI Summary · Claude Sonnet

Computer Science > Machine Learning [Submitted on 12 Mar 2026] Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency Xinyan Jiang, Wenjing Yu, Di Wang, Lijie Hu Activation engineering enables precise control over Large Language Models (LLMs) without the computational cost of fine-tuning. However, existing methods deriving vectors from static activation differences are susceptible to high-dimensional noise and layer-wise semantic drift, often capturing spurious correlations rather than the target intent. To address this, we propose Global Evolutionary Refined Steering (GER-steer), a training-free framework that grounded in the geometric stability of the network's representation evolution. GER-steer exploits this global signal to rectify raw steering vectors, effectively decoupling robust semantic intent from orthogonal artifacts. Extensive evaluations confirm that GER-steer consistently outperforms baselines, delivering superior efficacy and generalization without layer-specific tuning, establishing a universal solution for reliable model alignment. Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI) Cite as: arXiv:2603.12298 [cs.LG] (or arXiv:2603.12298v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2603.12298 Focus to learn more Submission history From: Xinyan Jiang [view email] [v1] Thu, 12 Mar 2026 03:45:19 UTC (1,106 KB) Access Paper: HTML (experimental) view license Current browse context: cs.LG < prev | next > new | recent | 2026-03 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

💬 Team Notes