Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models

• URL: http://arxiv.org/abs/2604.08297v1
• Date: Thu, 09 Apr 2026 14:31:42 GMT
• Title: Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models
• Abstract summary: Large Language Model (LLM) safety is crucial, yet the lack of a clear understanding about safety mechanisms hinders the development of precise and reliable methodologies for safety intervention.<n>We propose the Expected Safety Impact (ESI) framework for quantifying how different parameters affect LLM safety.
• Score: 39.89636417379952
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Ensuring Large Language Model (LLM) safety is crucial, yet the lack of a clear understanding about safety mechanisms hinders the development of precise and reliable methodologies for safety intervention across diverse tasks. To better understand and control LLM safety, we propose the Expected Safety Impact (ESI) framework for quantifying how different parameters affect LLM safety. Based on ESI, we reveal distinct safety-critical patterns across different LLM architectures: In dense LLMs, many safety-critical parameters are located in value matrices (V) and MLPs in middle layers, whereas in Mixture-of-Experts (MoE) models, they shift to the late-layer MLPs. Leveraging ESI, we further introduce two targeted intervention paradigms for safety enhancement and preservation, i.e., Safety Enhancement Tuning (SET) and Safety Preserving Adaptation (SPA). SET can align unsafe LLMs by updating only a few safety-critical parameters, effectively enhancing safety while preserving original performance. SPA safeguards well-aligned LLMs during capability-oriented intervention (e.g., instruction tuning) by preventing disruption of safety-critical weights, allowing the LLM to acquire new abilities and maintain safety capabilities. Extensive evaluations on different LLMs demonstrate that SET can reduce the attack success rates of unaligned LLMs by over 50% with only a 100-iteration update on 1% of model weights. SPA can limit the safety degradation of aligned LLMs within 1% after a 1,000-iteration instruction fine-tuning on different tasks. Our code is available at: https://github.com/ZJU-LLM-Safety/SafeWeights-ACL.

Related papers

• Distilling Safe LLM Systems via Soft Prompts for On Device Settings [15.154042788412879]
  This paper presents a study of parameter-efficient safety alignment methods for resource-constrained settings.<n>We identify that soft prompts combined with distillation-based training consistently outperform alternative methods.
  arXiv  Detail & Related papers  (2026-06-08T12:03:51Z)
• LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion [16.434293020863592]
  The safety mechanisms of large language models (LLMs) exhibit notable fragility, as even fine-tuning on datasets without harmful content may still undermine their safety capabilities.<n>We introduce LSSF, a novel safety re-alignment framework with underlineLow-Rank underlineSafety underlineSubspace underlineFusion.<n>Our proposed method exploits the low-rank characteristics of safety information in LLMs by constructing a low-rank projection matrix.
  arXiv  Detail & Related papers  (2026-01-19T03:59:12Z)
• UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models [67.91151588917396]
  Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak attacks.<n>We propose UpSafe$circ$C, a unified framework for enhancing LLM safety through safety-aware upcycling.<n>Our results highlight a new direction for LLM safety: moving from static alignment toward dynamic, modular, and inference-aware control.
  arXiv  Detail & Related papers  (2025-10-02T16:43:33Z)
• Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models [50.89022445197919]
  Large Audio Language Models (LALMs) have extended the capabilities of Large Language Models (LLMs)<n>Recent research has revealed that LALMs remain vulnerable to harmful queries due to insufficient safety-alignment.
  arXiv  Detail & Related papers  (2025-05-26T08:25:25Z)
• Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging [47.33307521558814]
  Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting.<n>We show that simply merging the weights of pre- and post-fine-tuned models effectively mitigates safety degradation while enhancing performance.
  arXiv  Detail & Related papers  (2024-12-27T08:03:22Z)
• Safety Layers in Aligned Large Language Models: The Key to LLM Security [43.805905164456846]
  Internal parameters in aligned LLMs can be vulnerable to security degradation when subjected to fine-tuning attacks.<n>Our work uncovers the mechanism behind security in aligned LLMs at the parameter level, identifying a small set of contiguous layers in the middle of the model.<n>We propose a novel fine-tuning approach, Safely Partial- Fine-Tuning (SPPFT), that fixes the gradient of the safety layers during fine-tuning to address the security degradation.
  arXiv  Detail & Related papers  (2024-08-30T04:35:59Z)
• 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)
• S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models [46.148439517272024]
  Generative large language models (LLMs) have revolutionized natural language processing with their transformative and emergent capabilities.<n>Recent evidence indicates that LLMs can produce harmful content that violates social norms.<n>We propose S-Eval, an automated Safety Evaluation framework with a newly defined comprehensive risk taxonomy.
  arXiv  Detail & Related papers  (2024-05-23T05:34:31Z)
• Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching [74.62818936088065]
  textscSafePatching is a novel framework for comprehensive PSA.<n>textscSafePatching achieves a more comprehensive PSA than baseline methods.<n>textscSafePatching demonstrates its superiority in continual PSA scenarios.
  arXiv  Detail & Related papers  (2024-05-22T16:51:07Z)
• Uncovering Safety Risks of Large Language Models through Concept Activation Vector [13.804245297233454]
  We introduce a Safety Concept Activation Vector (SCAV) framework to guide attacks on large language models (LLMs)<n>We then develop an SCAV-guided attack method that can generate both attack prompts and embedding-level attacks.<n>Our attack method significantly improves the attack success rate and response quality while requiring less training data.
  arXiv  Detail & Related papers  (2024-04-18T09:46:25Z)
• Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation [98.02846901473697]
  We propose ECSO (Eyes Closed, Safety On), a training-free protecting approach that exploits the inherent safety awareness of MLLMs. ECSO generates safer responses via adaptively transforming unsafe images into texts to activate the intrinsic safety mechanism of pre-aligned LLMs.
  arXiv  Detail & Related papers  (2024-03-14T17:03:04Z)

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.