OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization

• URL: http://arxiv.org/abs/2607.19806v2
• Date: Thu, 23 Jul 2026 05:44:07 GMT
• Title: OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization
• Abstract summary: Activation steering provides a lightweight mechanism for controlling large language models at inference time.<n>We introduce OPIUM, a training-free method for sanitizing steering vectors through representation matching.
• Score: 5.915252597405961
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Activation steering provides a lightweight mechanism for controlling large language models at inference time, but steering vectors can have unintended externalities: utility vectors may weaken safety behavior, while refusal vectors may induce over-refusal on benign prompts. We introduce OPIUM (Optimizing Protected Injections via Utility Manifolds), a training-free method for sanitizing steering vectors through representation matching. Given reference behaviors on two prompt sets, OPIUM optimizes a new steering vector that preserves the downstream representations induced by the desired intervention while matching a safer reference behavior on prompts where the original vector fails. Across steering-externality and over-refusal settings, OPIUM improves the safety--utility tradeoff relative to vanilla steering and directional ablation, suggesting that harmful side effects of activation steering can often be mitigated directly in activation space.

Related papers

• Safety Cost of Steering Vectors Is Separable and Reducible [15.133262969401004]
  Steering vectors can unintentionally compromise a model's safety mechanisms and increase compliance with harmful requests.<n>We show that this safety degradation arises from a separable component in the vector that disrupts the model's safety mechanisms but contributes little to the steering objective.<n>Our method substantially reduces steering-induced safety degradation while preserving the original steering effect with minimal impact on false refusal.
  arXiv  Detail & Related papers  (2026-08-09T00:29:54Z)
• 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)
• What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal [53.189667624047416]
  We show that different steering methodologies leverage functionally interchangeable circuits when applied at the same layer.<n>We show that steering vectors can be sparsified by up to 90-99% while retaining most performance.
  arXiv  Detail & Related papers  (2026-04-09T17:57:14Z)
• Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models [71.11171576590134]
  Vision-language models can be easily induced by visual jailbreak attacks to generate harmful content.<n>We propose NullSteer, a null-space projected activation defense framework.<n>We show that NullSteer significantly reduces harmful outputs under various jailbreak attacks.
  arXiv  Detail & Related papers  (2026-03-23T15:23:23Z)
• Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models [62.16655896700062]
  Activation steering is a technique to enhance the utility of Large Language Models (LLMs)<n>We show that it unintentionally introduces critical and under-explored safety risks.<n>Experiments reveal that these interventions act as a force multiplier, creating new vulnerabilities to jailbreaks and increasing attack success rates to over 80% on standard benchmarks.
  arXiv  Detail & Related papers  (2026-02-03T12:32:35Z)
• Self-Guard: Defending Large Reasoning Models via enhanced self-reflection [54.775612141528164]
  Self-Guard is a lightweight safety defense framework for Large Reasoning Models.<n>It bridges the awareness-compliance gap, achieving robust safety performance without compromising model utility.<n>Self-Guard exhibits strong generalization across diverse unseen risks and varying model scales.
  arXiv  Detail & Related papers  (2026-01-31T13:06:11Z)
• The Rogue Scalpel: Activation Steering Compromises LLM Safety [11.402179030703188]
  Activation steering is a technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference.<n>We demonstrate the opposite: steering systematically breaks model alignment safeguards, making it comply with harmful requests.
  arXiv  Detail & Related papers  (2025-09-26T08:49:47Z)
• AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint [49.641959856967276]
  We present a theoretically grounded and empirically effective activation steering method called AlphaSteer.<n>For utility preservation, it learns to construct a nearly zero vector for steering benign data, with the null-space constraints.<n>Experiments across multiple jailbreak attacks and utility benchmarks demonstrate the effectiveness of AlphaSteer.
  arXiv  Detail & Related papers  (2025-06-08T07:03:28Z)
• Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations [4.029252551781513]
  We propose a principled approach for uncovering steering vectors.<n>We focus on extracting latent risk preferences from large language models.<n>We show that the resulting steering vectors successfully and reliably modulate LLM outputs in line with the targeted behavior.
  arXiv  Detail & Related papers  (2025-05-16T18:23:10Z)
• One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs [21.2431937128876]
  We propose optimizing steering vectors through gradient descent on a single training example.<n>We find that the resulting SVs effectively mediate safety-relevant behaviors in multiple models.<n>We extend work on "emergent misalignment" and show that SVs optimized to induce a model to write vulnerable code cause the model to respond harmfully.
  arXiv  Detail & Related papers  (2025-02-26T06:13:01Z)
• Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization [34.05163996072159]
  "steering vectors" are extracted from the activations of human preference data. This work proposes an innovative approach that could produce more effective steering vectors through bi-directional preference optimization. Our method is designed to allow steering vectors to directly influence the generation probability of contrastive human preference data pairs.
  arXiv  Detail & Related papers  (2024-05-28T05:10:40Z)

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.