GEOSTEER: Geodesic Optimization for Activation Steering in Large Language Models

• URL: http://arxiv.org/abs/2609.10658v1
• Date: Wed, 09 Sep 2026 16:55:52 GMT
• Title: GEOSTEER: Geodesic Optimization for Activation Steering in Large Language Models
• Abstract summary: 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.
• Score: 9.438320824151157
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Activation steering provides a lightweight way to control large language models (LLMs) by modifying their hidden activations at inference time. Among these approaches, norm-preserving steering aims to change model behavior without altering the activation norm, reducing the risk of representation collapse and degradation. However, existing norm-preserving methods are limited by predefined steering trajectories and by their reliance on one-step updates, which may fail to capture the complex structure of activation distributions. We propose GeoSteer, an optimization-based method for norm-preserving activation steering. GeoSteer formulates steering as a Riemannian optimization problem and updates activations through a sequence of small geodesic steps on the representation manifold. To avoid fixed steering directions, GeoSteer learns a nonlinear activation-space objective that distinguishes desired from undesired activations, and uses this function to adaptively guide each steering step. This multistep formulation yields smoother, more stable, and more consistent steering behavior while preserving the activation norm. Across TruthfulQA, RealToxicityPrompts, and UltraFeedback benchmarks, GeoSteer consistently improves over state-of-the-art activation steering baselines. These results suggest that norm-preserving steering can be made more effective by replacing predefined one-step edits with adaptive, geometry-aware optimization.

Related papers

• Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation [74.17379276939599]
  We show that activation steering can induce broad misalignment, even in the recent Qwen-3.5 series.<n>We characterize properties of AS-induced EM by analyzing key steering-specific factors, including steering magnitude, the low-rank structure of the steering subspace, and the number of epochs during steering-vector construction.
  arXiv  Detail & Related papers  (2026-06-07T15:34:59Z)
• Minimizing Collateral Damage in Activation Steering [26.274685653829792]
  Activation steering is a method for controlling Large Language Model (LLM) behavior by intervening in its internal representations to increase the alignment with a specific target feature direction.<n>Standard interventions, such as vector addition, often cause unintended changes in the alignment of activations along other non-target feature directions.<n>In this work, we provide a mathematical formalization of collateral damage and introduce a principled framework that models steering as a constrained optimization problem.
  arXiv  Detail & Related papers  (2026-05-01T23:52:54Z)
• Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control [2.752817022620644]
  Inference-time LLM alignment methods offer an alternative to fine-tuning by directly modifying activations during generation.<n>We show that layer-wise dynamics across multiple LLM architectures and scales are well-approximated by locally-linear models.<n>We derive theoretical bounds on setpoint tracking error, enabling formal guarantees on steering performance.
  arXiv  Detail & Related papers  (2026-04-21T03:09:46Z)
• 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)
• Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency [12.78111885039368]
  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.
  arXiv  Detail & Related papers  (2026-03-12T03:45:19Z)
• Weight Updates as Activation Shifts: A Principled Framework for Steering [54.70188910511715]
  Activation steering promises to be an extremely parameter-efficient form of adaptation, but its effectiveness depends on critical design choices.<n>We establish a first-order equivalence between activation-space interventions and weight-space updates, deriving the conditions under which activation steering can replicate fine-tuning behavior.<n>This equivalence yields a principled framework for steering design and identifies the post-block output as a theoretically-backed and highly expressive intervention site.
  arXiv  Detail & Related papers  (2026-02-28T02:50:04Z)
• ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment [49.68063561145927]
  We propose a unified ordinary differential equations (ODEs)-based theoretical framework for activation steering.<n>We introduce ODESteer, a kind of ODE-based steering guided by barrier functions.<n>Compared to state-of-the-art activation steering methods, ODESteer achieves consistent empirical improvements.
  arXiv  Detail & Related papers  (2026-02-19T17:13:44Z)
• 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)
• Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection [1.7802147489386628]
  Large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors.<n>We propose Selective Steering, which addresses these limitations through two key innovations.<n> Experiments across nine models demonstrate that Selective Steering achieves 5.5x higher attack success rates than prior methods.
  arXiv  Detail & Related papers  (2026-01-27T08:56:25Z)
• GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters [61.51810815162003]
  We propose an SE(3)-equivariant adapter framework ( GeoAda) that enables flexible and parameter-efficient fine-tuning for controlled generative tasks.<n>GeoAda preserves the model's geometric consistency while mitigating overfitting and catastrophic forgetting.<n>We demonstrate the wide applicability of GeoAda across diverse geometric control types, including frame control, global control, subgraph control, and a broad range of application domains.
  arXiv  Detail & Related papers  (2025-07-02T18:44:03Z)

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.