arXiv Machine Learning
Jun 15
NeST: Neuron Selective Tuning for LLM Safety
arXiv:2602. 16835v2 Announce Type: replace-cross Abstract: Safety alignment is essential for the responsible deployment of Large Language Models (LLMs).
Safety Alignment via Constrained Knowledge Unlearning
The paper introduces Constrained Knowledge Unlearning (CKU), a safety alignment method that selectively prunes gradients of neurons in specific MLP layers to delete harmful knowledge while preserving useful information. CKU identifies a subset of neurons associated with valuable knowledge and protects them during the unlearning process, thereby mitigating jailbreak attacks. Experiments show that CKU improves model safety without sacrificing overall performance, and the study also offers insights into neuron knowledge sensitivity across MLP layers.
Related stories
arXiv AI
1d ago
Addition by Subtraction: Toward Mitigating Fragile Safety Alignment in Large Language Models
The paper introduces a method called Addition by Subtraction to strengthen safety alignment in large language models. By gradually removing identified safety‑critical neurons during finetuning and re‑optimizing preferences, the authors reduce the model’s reliance on sparse components that can be targeted by pruning or ablation attacks. Experiments on four models from three vendors show that this approach improves robustness to both white‑box and black‑box jailbreaks, lowers attack success rates by up to 90%, and enhances truthfulness while preserving general capabilities.
arXiv AI
Aug 26
NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
arXiv:2508.09473v2 Announce Type: replace-cross Abstract: Ensuring robust safety alignment while preserving utility is critical for the reliable deployment of Large Language Models (LLMs). However, c...
arXiv AI
Jun 2
SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
arXiv:2606. 02530v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax.
arXiv AI
Aug 26
NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution
NeuronGuard is a fine‑tuning defense for large language models that hardens them against both jailbreak and neuron‑level attacks. It redistributes safety signals across many neurons by identifying safety‑critical ones with per‑layer linear classifiers, enforcing refusal behavior when those neurons are ablated, and applying KL‑divergence regularization for consistency. A randomized gradient projection preserves task performance, and the authors provide a formal guarantee that NeuronGuard lowers the attack success rate upper bound, with experiments showing near‑zero success rates across multiple models and attack strategies.
arXiv AI
Oct 1
Faithful Dual-constrained Erasure for Robust LLM Safety Alignment
The paper introduces FDCU, a dual‑constrained subspace projection framework designed to improve machine unlearning for large language models. FDCU limits parameter updates with a dual‑masking rule that preserves general knowledge via Fisher Information while preventing the activation of spurious suppressors through the Principle of Minimal Functional Intervention. Experiments show that FDCU achieves state‑of‑the‑art robustness against retraining attacks while maintaining near‑lossless general utility, thereby ensuring durable safety for LLMs.
arXiv AI
Aug 11
Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways
arXiv:2608. 09095v1 Announce Type: new Abstract: Uncovering the internal mechanisms underlying the safety capabilities of large language models (LLMs) is crucial for developing trustworthy artificial intelligence.
arXiv AI
Jul 23
Matching Ranks Over Probability Yields Truly Deep Safety Alignment
arXiv:2512. 05518v2 Announce Type: replace-cross Abstract: Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their "open" nature introduces more avenues for malicious actors to misuse them for harmful purposes.
arXiv Machine Learning
Jun 2
Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
arXiv:2606. 00686v1 Announce Type: new Abstract: The prevailing paradigm in large language model (LLM) alignment operates via erasure, filtering unsafe data or training models to strictly refuse harmful prompts.
arXiv AI
Aug 24
RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
arXiv:2605.01913v2 Announce Type: replace-cross Abstract: Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vul...
arXiv AI
Oct 21
Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation
arXiv:2610.26443v2 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) on downstream tasks often weakens their previously aligned safety behavior, creating an inherent tra...
arXiv AI
Sep 2
From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling
arXiv:2609.00051v1 Announce Type: cross Abstract: Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the...