High-Dimensional Random Projection for Activation Steering in Language Models

• URL: http://arxiv.org/abs/2606.15092v1
• Date: Sat, 13 Jun 2026 03:53:23 GMT
• Title: High-Dimensional Random Projection for Activation Steering in Language Models
• Abstract summary: We propose High-Dimensional Random-projection for Activation Steering (HiDRA)<n>HiDRA is a training-free approach that integrates seamlessly with existing activation steering methods.<n> Experiments across diverse LLM families and benchmarks demonstrate that HiDRA consistently outperforms baseline counterparts.
• Score: 15.283548146322977
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Activation steering has emerged as a key methodology for controlling the behavior of large language models (LLMs). Existing difference-in-means based methods, however, are fundamentally limited: they capture only mean differences between class activations and fail to recover discriminative signals that naturally exist in the nonlinear feature subspace under the superposition hypothesis. Motivated by that, we propose High-Dimensional Random-projection for Activation Steering (HiDRA), a training-free approach that integrates seamlessly with existing activation steering methods. By performing activation addition in the projected high-dimensional space, HiDRA can provably capture a better discriminative structure beyond the reach of linear methods. Experiments across diverse LLM families and benchmarks demonstrate that HiDRA consistently outperforms baseline counterparts, achieving stronger behavioral control without significant computational overhead.

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)
• Latent Action Reparameterization for Efficient Agent Inference [56.42014061367112]
  We propose a framework that learns a compact latent action space in which each latent action corresponds to a multi-step semantic behavior.<n>Unlike hand-crafted macros or hierarchical controllers, latent actions are learned from agent trajectories and integrated directly into the model.
  arXiv  Detail & Related papers  (2026-05-18T16:07:44Z)
• 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)
• 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)
• Mechanistic Indicators of Steering Effectiveness in Large Language Models [3.635648354808971]
  Activation-based steering enables Large Language Models to exhibit targeted behaviors by intervening on intermediate activations without retraining.<n>Despite its widespread use, the mechanistic factors that govern when steering succeeds or fails remain poorly understood.<n>We investigate whether the reliability of steering can be diagnosed using internal model signals.
  arXiv  Detail & Related papers  (2026-02-02T06:56:22Z)
• Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective [85.06838178922791]
  Reinforcement Learning (RL) has proven highly effective for autoregressive language models.<n>But adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges.<n>We propose a principled RL framework that treats entire sequence generation as a single action and uses the ELBO as a tractable sequence-level likelihood proxy.
  arXiv  Detail & Related papers  (2025-12-03T13:05:32Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Learning Distribution-Wise Control in Representation Space for Language Models [7.756342860929851]
  Learnable interventions aim to apply pointwise control within the concept subspace and have proven effective in altering high-level behaviors.<n>We extend this approach to the distribution level, enabling the model to learn not only pointwise transformations but also the surrounding regions of the concept subspace.
  arXiv  Detail & Related papers  (2025-06-07T06:52:58Z)
• Probe-Free Low-Rank Activation Intervention [26.502232859901167]
  Inference-time interventions that edit the hidden activations have shown promising results in steering the LMs towards desirable generations.<n>This paper proposes a probe-free intervention method FLORAIN for all attention heads in a specific activation layer.
  arXiv  Detail & Related papers  (2025-02-06T13:03:05Z)
• Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors [8.761404991620285]
  Activation intervention has emerged as an effective and economical method to modify the behavior of large language models (LLMs)<n>We propose Semantics-Adaptive Dynamic Intervention (SADI), a novel method that constructs a dynamic steering vector to intervene model activations at inference time.<n> Experimental results show that SADI outperforms established baselines by substantial margins, improving task performance without training.
  arXiv  Detail & Related papers  (2024-10-16T06:58:49Z)
• InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance [56.184255657175335]
  We develop textbfInferAligner, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks.
  arXiv  Detail & Related papers  (2024-01-20T10:41:03Z)

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.