SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs

Shaona Ghosh; Amrita Bhattacharjee; Yftah Ziser; Christopher Parisien

Home/Archive/arXiv

arXiv · 2506.04250

SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs

Shaona Ghosh·Amrita Bhattacharjee·Yftah Ziser·Christopher Parisien

View original source ↗Read source document ↗Export metadata ↓

Abstract

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise, customizable safety adjustments remains largely untapped. This paper investigates an approach called SafeSteer for guiding the outputs of LLMs by: (i) leveraging category-specific steering vectors for more precise control, (ii) employing a simple, gradient-free unsupervised method to enhance safety steering while preserving text quality, topic relevance, and without explicit refusal, and (iii) accomplishing this without a hard requirement of contrastive pairwise safe data. We also highlight that our method, being simple and effective, aligns with recent studies suggesting that simple techniques often outperform more complex ones in activation steering. We showcase the effectiveness of our approach across various LLMs, datasets, and risk categories, demonstrating its ability to provide precise control, prevent blanket refusals, and guide models toward generating safe content while maintaining topic relevance.

Explore related subjects

cs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Shaona Ghosh, Amrita Bhattacharjee, Yftah Ziser, Christopher Parisien. 2025-06-01. SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs. https://arxiv.org/abs/2506.04250

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Random Polytope Descriptors

We introduce a class of random polytopes which simultaneously generalizes several known constructions. While being fairly general, these polytopes are also computationally exceptionally benign. We indicate how these properties can be exploited for classification and clustering tasks in data analysis. Crucially, our construction lets users smoothly trade off between a tighter description of the data and faster computation.

cs.LG↗

arXiv2026

CurvFed: Curvature-Aligned Federated Learning for Fairness without Demographics

Modern human sensing applications often rely on data distributed across users and devices, where privacy concerns prevent centralized training. Federated Learning (FL) addresses this challenge by enabling collaborative model training without exposing raw data or attributes. However, achieving fairness in such settings remains difficult, as most human sensing datasets lack demographic labels, and FL's privacy guarantees limit the use of sensitive attributes. This paper introduces CurvFed: Curvature Aligned Federated Learning for Fairness without Demographics, a theoretically grounded framework that promotes fairness in FL without requiring any demographic or sensitive attribute information, a concept termed Fairness without Demographics (FWD), by optimizing the underlying loss landscape curvature. Building on the theory that equivalent loss landscape curvature corresponds to consistent model efficacy across sensitive attribute groups, CurvFed regularizes the top eigenvalue of the Fisher Information Matrix (FIM) as an efficient proxy for loss landscape curvature, both within and across clients. This alignment promotes uniform model behavior across diverse bias inducing factors, offering an attribute agnostic route to algorithmic fairness. CurvFed is especially suitable for real world human sensing FL scenarios involving single or multi user edge devices with unknown or multiple bias factors. We validated CurvFed through theoretical and empirical justifications, as well as comprehensive evaluations using three real world datasets and a deployment on a heterogeneous testbed of resource constrained devices. Additionally, we conduct sensitivity analyses on local training data volume, client sampling, communication overhead, resource costs, and runtime performance to demonstrate its feasibility for practical FL edge device deployment.

cs.LG↗

arXiv2026

Path Regularization: A Near-Complete and Optimal Nonasymptotic Generalization Theory for Multilayer Neural Networks and Double Descent Phenomenon

Path regularization has shown to be a very effective regularization to train neural networks, leading to a better generalization property than common regularizations i.e. weight decay, etc. We propose a first near-complete (as will be made explicit in the main text) nonasymptotic generalization theory for multilayer neural networks with path regularizations for general learning problems. In particular, it does not require the boundedness of the loss function, as is commonly assumed in the literature. Our theory goes beyond the bias-variance tradeoff and aligns with phenomena typically encountered in deep learning. It is therefore sharply different from other existing nonasymptotic generalization error bounds. More explicitly, we propose an explicit generalization error upper bound for multilayer neural networks with $σ(0)=0$ and sufficiently broad Lipschitz loss functions, without requiring the width, depth, or other hyperparameters of the neural network to approach infinity, a specific neural network architecture (e.g., sparsity), or boundedness of the loss function, while also taking approximation error into consideration. In particular, we solve an open problem proposed by Weinan E et. al. in 2020 regarding the approximation rates in generalized Barron spaces. Furthermore, we show the near-minimax optimality of our theory for regression problems with ReLU activations. Notably, our upper bound exhibits the famous double descent phenomenon for such networks, which is the most distinguished characteristic compared with other existing results. Our subsequent work will prove the matching lower bounds in the minimax sense, meaning that it is highly possible that our theory reveals the true underlying mechanism of the double descent phenomenon. We can also explain scaling law from this theory.

cs.LG↗