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

• URL: http://arxiv.org/abs/2603.12298v1
• Date: Thu, 12 Mar 2026 03:45:19 GMT
• Title: Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
• Abstract summary: Activation engineering enables precise control over Large Language Models (LLMs) without the computational cost of fine-tuning.<n>Existing methods deriving vectors from static activation differences are susceptible to high-dimensional noise and layer-wise semantic drift.<n>We propose Global Evolutionary Refined Steering (GER-steer), a training-free framework that grounded in the geometric stability of the network's representation evolution.
• Score: 12.78111885039368
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 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.

Related papers

• GEOSTEER: Geodesic Optimization for Activation Steering in Large Language Models [9.438320824151157]
  We propose GeoSteer, an optimization-based method for norm-preserving activation steering.<n>We show that GeoSteer consistently improves over state-of-the-art activation steering baselines.<n>These results suggest that norm-preserving steering can be made more effective by replacing predefined one-step edits with adaptive, geometry-aware optimization.
  arXiv  Detail & Related papers  (2026-09-09T16:55:52Z)
• IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning [57.16513298507272]
  We propose IADD-TR, a unified framework combining Intervention-Aware Dynamics Decoupling (IADD) and Targeted Regularization (TR)<n>IADD factorizes transitions into an action-intervention stage and an action-free natural evolution stage, using a zero-action anchor to resolve the non-uniqueness of this two-stage factorization for robust generalization.<n>For policy learning, we derive TR from the efficient influence function of a replay-state policy-gradient functional.
  arXiv  Detail & Related papers  (2026-08-11T08:20:02Z)
• Mitigating Error Amplification in Fast Adversarial Training [58.74042726356826]
  Fast Adversarial Training (FAT) has proven effective in enhancing model robustness by encouraging networks to learn perturbation-invariant representations.<n>FAT often suffers from catastrophic overfitting (CO), where the model overfits to the training attack and fails to generalize to unseen ones.<n>We propose a Distribution-aware Dynamic Guidance (DDG) strategy that dynamically adjusts both the perturbation budget and supervision signal.
  arXiv  Detail & Related papers  (2026-04-27T11:23:18Z)
• AnchorRefine: Synergy-Manipulation Based on Trajectory Anchor and Residual Refinement for Vision-Language-Action Models [60.04879435087352]
  Vision-language-action (VLA) policies generate actions within a single unified space.<n>We propose AnchorRefine, a hierarchical framework that factorizes VLA action modeling into trajectory anchor and residual refinement.<n> Experiments on LIBERO, CALVIN, and real-robot tasks demonstrate that AnchorRefine consistently improves both regression-based and diffusion-based VLA backbones.
  arXiv  Detail & Related papers  (2026-04-20T04:25:24Z)
• Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection [8.819278296219071]
  Large Language Models (LLMs) often fail to follow complex user instructions.<n> Activation steering techniques aim to manipulate model internals, but have a potential risk of oversteering.<n>We introduce DIRECTER, a novel steering method that dynamically modulates steering strength by scaling the KV cache without extra dataset.
  arXiv  Detail & Related papers  (2026-03-06T09:49:32Z)
• OmniVL-Guard: Towards Unified Vision-Language Forgery Detection and Grounding via Balanced RL [63.388513841293616]
  Existing forgery detection methods fail to handle the interleaved text, images, and videos prevalent in real-world misinformation.<n>To bridge this gap, this paper targets to develop a unified framework for omnibus vision-language forgery detection and grounding.<n>We propose textbf OmniVL-Guard, a balanced reinforcement learning framework for omnibus vision-language forgery detection and grounding.
  arXiv  Detail & Related papers  (2026-02-11T09:41:36Z)
• Steer2Edit: From Activation Steering to Component-Level Editing [24.755027943286432]
  We propose Steer2Edit, a training-free framework that transforms steering vectors into diagnostic signals for component rank-1 weight editing.<n>Across safety alignment, attribute mitigation, and reasoning efficiency, Steer2Edit consistently achieves more favorable attribute-utility trade-offs.<n>Overall, Steer2Edit provides a principled bridge between representation steering and weight editing.
  arXiv  Detail & Related papers  (2026-02-10T15:15:15Z)
• Spherical Steering: Geometry-Aware Activation Rotation for Language Models [15.078810641141295]
  Inference-time steering has emerged as a promising paradigm for controlling language models (LMs) without the cost of retraining.<n>In this work, we explore Spherical Steering, a training-free primitive that resolves this trade-off through activation rotation.<n>Our method rotates activations along a geodesic toward a target direction, guiding the activation toward the target concept while preserving the integrity of the signal.
  arXiv  Detail & Related papers  (2026-02-09T00:15:47Z)
• Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics [81.80010043113445]
  Local weight fine-tuning, LoRA-based adaptation, and activation-based interventions are studied in isolation.<n>We present a unified view that frames these interventions as dynamic weight updates induced by a control signal.<n>Across methods, we observe a consistent trade-off between preference and utility: stronger control increases preference while predictably reducing utility.
  arXiv  Detail & Related papers  (2026-02-02T17:04:36Z)
• Dynamically Scaled Activation Steering [3.177576903071419]
  We introduce Dynamically Scaled Activation Steering (DSAS), a method-agnostic steering framework that decouples when to steer from how to steer.<n>DSAS adaptively modulates the strength of existing steering transformations across layers and inputs, intervening strongly only when undesired behavior is detected.
  arXiv  Detail & Related papers  (2025-12-03T10:50:15Z)
• Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation [60.04281435591454]
  CRDA (Curriculum Reinforcement-Learning Data Augmentation) is a novel framework guiding detectors to progressively master multi-domain forgery features.<n>Central to our approach is integrating reinforcement learning and causal inference.<n>Our method significantly improves detector generalizability, outperforming SOTA methods across multiple cross-domain datasets.
  arXiv  Detail & Related papers  (2025-11-10T12:45:52Z)
• Activation Steering with a Feedback Controller [4.609594868699996]
  Proportional-Integral-Derivative (PID) Steering is a principled framework that leverages the full PID controller for activation steering in large language models.<n>PID Steering consistently outperforms existing approaches, achieving more robust and reliable behavioral control.
  arXiv  Detail & Related papers  (2025-10-05T18:05:28Z)
• GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs [56.93583799109029]
  GrAInS is an inference-time steering approach that operates across both language-only and vision-language models and tasks.<n>During inference, GrAInS hidden activations at transformer layers guided by token-level attribution signals, and normalizes activations to preserve representational scale.<n>It consistently outperforms both fine-tuning and existing steering baselines.
  arXiv  Detail & Related papers  (2025-07-24T02:34:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.