Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs

ACL ARR 2026 January Submission2024 Authors

Keywords: applications, safety and alignment, security and privacy, pruning

Abstract:

Machine learning models are increasingly deployed in real-world applications, but even aligned models such as Mistral and LLaVA still exhibit unsafe behaviors inherited from pre-training.
Current alignment methods like SFT and RLHF primarily encourage models to generate preferred responses, but do not explicitly remove the unsafe subnetworks that trigger harmful outputs.
In this work, we introduce a resource-efficient pruning framework that directly identifies and removes parameters associated with unsafe behaviors while preserving model utility.
Our method employs a gradient-free attribution mechanism, requiring only modest GPU resources, and generalizes across architectures and quantized variants.
Empirical evaluations on ML models show substantial reductions in unsafe generations and improved robustness against jailbreak attacks, with minimal utility loss.
From the perspective of the Lottery Ticket Hypothesis, our results suggest that ML models contain “unsafe tickets” responsible for harmful behaviors, and pruning reveals “safety tickets” that maintain performance while aligning outputs.
This provides a lightweight, post-hoc alignment strategy suitable for deployment in resource-constrained settings.

Paper Type: Long

Research Area: Language Models

Research Area Keywords: applications,safety and alignment,security and privacy,pruning

Contribution Types: Approaches to low-resource settings, Approaches low compute settings-efficiency

Languages Studied: English

Submission Number: 2024