Expert-Aware Refusal Steering

• URL: http://arxiv.org/abs/2606.04160v1
• Date: Tue, 02 Jun 2026 19:23:46 GMT
• Title: Expert-Aware Refusal Steering
• Abstract summary: Safety alignment in instruction-tuned large language models (LLMs) depends on a model's ability to reliably refuse to respond to harmful or disallowed requests.<n>Recent work has shown that a steering vector can be applied to a dense LLM during inference to effectively suppress refusal behavior.<n>We propose two expert-aware refusal steering methods that leverage refusal-specific expert routing patterns and expert-specific steering directions to suppress normal refusal behavior.
• Score: 2.0391237204597368
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Safety alignment in instruction-tuned large language models (LLMs) depends on a model's ability to reliably refuse to respond to harmful or disallowed requests. Recent work has shown that a steering vector can be applied to a dense LLM during inference to effectively suppress refusal behavior, inducing response to harmful requests. We extend this refusal steering method to three open-source Mixture-of-Experts (MoE) LLMs and find that steering performance is uninhibited by the complex routing patterns inherent to the MoE architecture. We then propose two expert-aware refusal steering methods that leverage refusal-specific expert routing patterns and expert-specific steering directions to suppress normal refusal behavior. We find that refusal behavior can be effectively steered based on the output of a single expert. Our results show that refusal signals captured by steering methods differ from expert routing behavior, suggesting a substantial role for attention in MoE refusal behavior.

Related papers

• Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning [109.33717747526583]
  Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks.<n>We introduce textbfCaRL (textbfCapability-textbfaligned textbfReinforcement textbfL) to align behavior with capability boundaries.<n>Experiments demonstrate a substantial reduction in futile reasoning while preserving performance across task difficulties.
  arXiv  Detail & Related papers  (2026-07-31T09:30:33Z)
• Understanding Safety-Sensitive Expert Behavior in Mixture-of-Experts LLMs [21.519746366998646]
  A common intuition is that safety behavior may be controlled by routing harmful requests to distinct refusal-oriented experts.<n>We present **RASET**, a framework that probes safety enforcement that is localized in a small subset of experts.<n>Results reveal a distinct MoE safety risk, highlighting the need for expert-aware alignment mechanisms.
  arXiv  Detail & Related papers  (2026-05-28T10:09:51Z)
• CRaFT: Circuit-Guided Refusal Feature Selection via Cross-Layer Transcoders [10.526176863220988]
  We propose a circuit-guided refusal feature selection framework that ranks features by their influence on the model's refusal-compliance decision.<n>On Gemma-3-1B-it, CRaFT improves attack success rate (ASR) from 6.7% to 48.2% and outperforms baseline methods.
  arXiv  Detail & Related papers  (2026-04-02T04:28:11Z)
• From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions [7.599054770990825]
  We leverage a version of Llama 3 8B fine-tuned with categorical refusal tokens to enable inference-time control over fine-grained refusal behavior.<n>We construct categorical steering vectors with a lightweight probe that determines whether to steer toward or away from refusal during inference.<n>Across benchmarks, both categorical steering vectors and the low-rank combination consistently reduce over-refusals on benign prompts while increasing refusal rates on harmful prompts.
  arXiv  Detail & Related papers  (2026-03-09T06:37:16Z)
• Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics [2.4839105527363574]
  We introduce Refusal Steering, an inference-time method to exercise fine-grained control over Large Language Models refusal behaviour.<n>We show that it can remove political refusal behaviour while retaining safety alignment for harmful content.
  arXiv  Detail & Related papers  (2025-12-18T14:43:04Z)
• Learning to Steer: Input-dependent Steering for Multimodal LLMs [54.41165851011022]
  In this paper, we investigate a fine-grained steering that uses an input-specific linear shift.<n>We train a small auxiliary module to predict the input-specific steering vector.<n>Our approach, dubbed as L2S (Learn-to-Steer), demonstrates that it reduces hallucinations and enforces safety in MLLMs, outperforming other static baselines.
  arXiv  Detail & Related papers  (2025-08-18T10:53:20Z)
• COSMIC: Generalized Refusal Direction Identification in LLM Activations [43.30637889861949]
  We introduce bfCOSMIC (Cosine Similarity Metrics for Inversion of Concepts), an automated framework for direction selection.<n>It identifies viable steering directions and target layers using cosine similarity - entirely independent of model outputs.<n>It reliably identifies refusal directions in adversarial settings and weakly aligned models, and is capable of steering such models toward safer behavior with minimal increase in false refusals.
  arXiv  Detail & Related papers  (2025-05-30T04:54:18Z)
• Understanding Refusal in Language Models with Sparse Autoencoders [27.212781538459588]
  We use sparse autoencoders to identify latent features that causally mediate refusal behaviors.<n>We intervene on refusal-related features to assess their influence on generation.<n>This enables a fine-grained inspection of how refusal manifests at the activation level.
  arXiv  Detail & Related papers  (2025-05-29T15:33:39Z)
• Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction [68.6543680065379]
  Large language models (LLMs) are vulnerable to prompt injection attacks.<n>We propose a novel defense method that leverages, rather than suppresses, the instruction-following abilities of LLMs.
  arXiv  Detail & Related papers  (2025-04-29T07:13:53Z)
• Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior [59.20260988638777]
  We demonstrate that prompting safety reflection before generating a response can mitigate false refusal behavior.<n>In an ablation study across 15 pre-trained models, we show that models fine-tuned with safety reflection significantly reduce false refusal behavior.
  arXiv  Detail & Related papers  (2025-03-22T23:35:49Z)
• The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence [57.57786477441956]
  Prior work suggests that a single refusal direction in the model's activation space determines whether an LLM refuses a request.<n>We propose a novel gradient-based approach to representation engineering and use it to identify refusal directions.<n>We show that refusal mechanisms in LLMs are governed by complex spatial structures and identify functionally independent directions.
  arXiv  Detail & Related papers  (2025-02-24T18:52:59Z)
• On Prompt-Driven Safeguarding for Large Language Models [172.13943777203377]
  We find that in the representation space, the input queries are typically moved by safety prompts in a "higher-refusal" direction. Inspired by these findings, we propose a method for safety prompt optimization, namely DRO. Treating a safety prompt as continuous, trainable embeddings, DRO learns to move the queries' representations along or opposite the refusal direction, depending on their harmfulness.
  arXiv  Detail & Related papers  (2024-01-31T17:28:24Z)

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.