Dynamically Scaled Activation Steering

• URL: http://arxiv.org/abs/2512.03661v1
• Date: Wed, 03 Dec 2025 10:50:15 GMT
• Title: Dynamically Scaled Activation Steering
• Authors: Alex Ferrando, Xavier Suau, Jordi Gonzàlez, Pau Rodriguez,
• Abstract summary: 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.
• Score: 3.177576903071419
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation. However, most existing methods apply interventions uniformly across all inputs, degrading model performance when steering is unnecessary. We introduce Dynamically Scaled Activation Steering (DSAS), a method-agnostic steering framework that decouples when to steer from how to steer. DSAS adaptively modulates the strength of existing steering transformations across layers and inputs, intervening strongly only when undesired behavior is detected. At generation time, DSAS computes context-dependent scaling factors that selectively adjust the strength of any steering method. We also show how DSAS can be jointly optimized end-to-end together with the steering function. When combined with existing steering methods, DSAS consistently improves the Pareto front with respect to steering alone, achieving a better trade-off between toxicity mitigation and utility preservation. We further demonstrate DSAS's generality by applying it to a text-to-image diffusion model, showing how adaptive steering allows the modulation of specific concepts. Finally, DSAS introduces minimal computational overhead while improving interpretability, pinpointing which tokens require steering and by how much.

Related papers

• 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)
• AMPS: Adaptive Modality Preference Steering via Functional Entropy [66.69992693275061]
  We introduce an instance-aware diagnostic metric that quantifies each modality's information contribution and reveals sample-specific susceptibility to steering.<n> Experimental results show that our instance-aware steering outperforms conventional steering in modulating modality preference.
  arXiv  Detail & Related papers  (2026-02-13T02:29:06Z)
• Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions [37.08071497197165]
  Intervention-based model steering offers a lightweight and interpretable alternative to prompting and fine-tuning.<n>We build on the principles of distributed alignment search to propose a new steering method: Concept DAS.<n>We show that Concept DAS does not always outperform preference-optimization methods but may benefit more from increased model scale.
  arXiv  Detail & Related papers  (2026-02-05T02:51:00Z)
• Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations [55.047454145941366]
  Streaming Merging is an innovative model updating paradigm that conceptualizes merging as an iterative optimization process.<n> ARM is a strategy designed to approximate gradient descent dynamics.<n> ARM requires only early SFT checkpoints and, through iterative merging, surpasses the fully converged SFT model.
  arXiv  Detail & Related papers  (2026-02-03T08:15:57Z)
• 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)
• 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)
• KV Cache Steering for Controlling Frozen LLMs [80.50365534625438]
  cache steering is a lightweight method for implicit steering of language models.<n>We apply cache steering to induce chain-of-thought reasoning in small language models.
  arXiv  Detail & Related papers  (2025-07-11T17:59:36Z)
• Improved Representation Steering for Language Models [50.86411958644953]
  We show how to improve representation steering via our new Reference-free Preference Steering (RePS)<n>On Gemma models with sizes ranging from 2B to 27B, RePS outperforms all existing steering methods trained with a language modeling objective.<n>In suppression, RePS matches the language-modeling objective on Gemma-2 and outperforms it on the larger Gemma-3 variants.
  arXiv  Detail & Related papers  (2025-05-27T07:16:40Z)
• Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms [71.85633762642125]
  The vast number of parameters in models often results in highly intertwined internal representations.<n>Recent research has explored the use of sparse autoencoders (SAE) to disentangle knowledge in high-dimensional spaces for steering.<n>We propose Steering Target Atoms (STA), a novel method that isolates and manipulates disentangled knowledge components to enhance safety.
  arXiv  Detail & Related papers  (2025-05-23T17:59:18Z)
• Steering Large Language Model Activations in Sparse Spaces [21.55545768931058]
  A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time.<n>We introduce sparse activation steering (SAS), a method that leverages sparse autoencoders (SAEs) to steer behavior in sparse spaces.
  arXiv  Detail & Related papers  (2025-02-28T20:43:45Z)
• Interpretable Steering of Large Language Models with Feature Guided Activation Additions [4.496738719682736]
  We introduce Feature Guided Activation Additions (FGAA), a novel activation steering method.<n>By operating in the latent space of a Sparse Autoencoder (SAE), FGAA constructs precise steering vectors.<n> evaluations on Gemma-2-2B and Gemma-2-9B models demonstrate that FGAA outperforms existing steering methods.
  arXiv  Detail & Related papers  (2025-01-17T02:55:23Z)
• Analyzing the Generalization and Reliability of Steering Vectors [8.253773195379166]
  We show that steering vectors have substantial limitations both in- and out-of-distribution.<n>In-distribution, steerability is highly variable across different inputs.<n>Out-of-distribution, while steering vectors often generalise well, for several concepts they are brittle to reasonable changes in the prompt.
  arXiv  Detail & Related papers  (2024-07-17T08:32:03Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)

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.