AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin

• URL: http://arxiv.org/abs/2506.08473v2
• Date: Wed, 11 Jun 2025 02:43:10 GMT
• Title: AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin
• Authors: Shuo Yang, Qihui Zhang, Yuyang Liu, Yue Huang, Xiaojun Jia, Kunpeng Ning, Jiayu Yao, Jigang Wang, Hailiang Dai, Yibing Song, Li Yuan,
• Abstract summary: Large language models (LLMs) are vulnerable to safety risks during fine-tuning.<n>We propose a methodology for safety fine-tuning called AsFT (Anchoring Safety in Fine-Tuning)
• Score: 38.577959886489076
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) are vulnerable to safety risks during fine-tuning, where small amounts of malicious or harmless data can compromise safeguards. In this paper, building on the concept of alignment direction -- defined by the weight difference between aligned and unaligned models -- we observe that perturbations along this direction preserve model safety. In contrast, perturbations along directions orthogonal to this alignment are strongly linked to harmful direction perturbations, rapidly degrading safety and framing the parameter space as a narrow safety basin. Based on this insight, we propose a methodology for safety fine-tuning called AsFT (Anchoring Safety in Fine-Tuning), which integrates a regularization term into the training objective. This term uses the alignment direction as an anchor to suppress updates in harmful directions, ensuring that fine-tuning is constrained within the narrow safety basin. Extensive experiments on multiple datasets show that AsFT outperforms Safe LoRA, reducing harmful behavior by 7.60 percent, improving model performance by 3.44 percent, and maintaining robust performance across various experimental settings. Code is available at https://github.com/PKU-YuanGroup/AsFT

Related papers

• AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization [6.5225344327304535]
  Low-rank adaptation (LoRA) has become a standard tool for efficiently fine-tuning large language models.<n>LoRA updates can induce alignment drift, weakening safety and behavioral constraints.<n>We propose AlignGuard-LoRA, a principled framework for preserving alignment during finetuning.
  arXiv  Detail & Related papers  (2025-08-04T05:45:24Z)
• Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs [4.580092836731863]
  Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enhances adaptability while reducing computational costs.<n>Existing safety alignment methods struggle to capture complex parameter shifts, leading to suboptimal safety-utility trade-offs.<n>We propose Safe Pruning LoRA (SPLoRA), a novel pruning-based approach that selectively removes LoRA layers that weaken safety alignment.
  arXiv  Detail & Related papers  (2025-06-21T14:59:54Z)
• Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets [64.96967819446553]
  This paper investigates the degradation of safety guardrails through the lens of representation similarity between upstream alignment datasets and downstream fine-tuning tasks.<n>High similarity between these datasets significantly weakens safety guardrails, making models more susceptible to jailbreaks.<n>Low similarity between these two types of datasets yields substantially more robust models and thus reduces harmfulness score by up to 10.33%.
  arXiv  Detail & Related papers  (2025-06-05T17:59:55Z)
• Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment [4.181987990532721]
  Existing paradigms for ensuring AI safety, such as guardrail models and alignment training, often compromise either inference efficiency or development flexibility.<n>We introduce Disentangled Safety Adapters (DSA), a novel framework addressing these challenges by decoupling safety-specific computations from a task-optimized base model.<n>DSA utilizes lightweight adapters that leverage the base model's internal representations, enabling diverse and flexible safety functionalities with minimal impact on inference cost.
  arXiv  Detail & Related papers  (2025-05-30T19:11:52Z)
• Shape it Up! Restoring LLM Safety during Finetuning [66.46166656543761]
  Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks.<n>We propose dynamic safety shaping (DSS), a framework that uses fine-grained safety signals to reinforce learning from safe segments of a response while suppressing unsafe content.<n>We present STAR-DSS, guided by STAR scores, that robustly mitigates finetuning risks and delivers substantial safety improvements across diverse threats, datasets, and model families.
  arXiv  Detail & Related papers  (2025-05-22T18:05:16Z)
• SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging [38.69546578029726]
  We propose SafeMERGE, a post-fine-tuning framework that preserves safety while maintaining task utility.<n>We evaluate SafeMERGE against other fine-tuning- and post-fine-tuning-stage approaches for Llama-2-7B-Chat and Qwen-2-7B-Instruct models.
  arXiv  Detail & Related papers  (2025-03-21T15:44:09Z)
• Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models [30.93821289892195]
  We propose IRR (Identify, Remove, and Recalibrate for Safety Realignment) that performs safety realignment for LLMs.<n>The core of IRR is to identify and remove unsafe delta parameters from the fine-tuned models, while recalibrating the retained ones.<n>Our results demonstrate that IRR significantly enhances the safety performance of fine-tuned models on safety benchmarks, such as harmful queries and jailbreak attacks.
  arXiv  Detail & Related papers  (2024-12-15T03:58:38Z)
• What Makes and Breaks Safety Fine-tuning? A Mechanistic Study [64.9691741899956]
  Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. We design a synthetic data generation framework that captures salient aspects of an unsafe input. Using this, we investigate three well-known safety fine-tuning methods.
  arXiv  Detail & Related papers  (2024-07-14T16:12:57Z)
• Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models [65.06446825020578]
  Safety alignment is crucial to ensure that large language models (LLMs) behave in ways that align with human preferences and prevent harmful actions during inference. We aim to measure the risks in finetuning LLMs through navigating the LLM safety landscape.
  arXiv  Detail & Related papers  (2024-05-27T17:31:56Z)
• Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! [88.90694413503614]
  We find that the safety alignment of LLMs can be compromised by fine-tuning. We jailbreak GPT-3.5 Turbo's safety guardrails by fine-tuning it on only 10 such examples. We advocate for further research efforts toward reinforcing safety protocols for the custom fine-tuning of aligned LLMs.
  arXiv  Detail & Related papers  (2023-10-05T17:12:17Z)

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.