Harmonious Parameter Adaptation in Continual Visual Instruction Tuning for Safety-Aligned MLLMs
- URL: http://arxiv.org/abs/2511.20158v1
- Date: Tue, 25 Nov 2025 10:34:51 GMT
- Title: Harmonious Parameter Adaptation in Continual Visual Instruction Tuning for Safety-Aligned MLLMs
- Authors: Ziqi Wang, Chang Che, Qi Wang, Hui Ma, Zenglin Shi, Cees G. M. Snoek, Meng Wang,
- Abstract summary: Harmonious Adaptation (HPA) is a post-training framework composed of focusing-based parameter partition, harmonious balanced parameter selection, and parameter adjustment.<n>HPA better maintains high safety and mitigates forgetting than existing baselines.<n> experiments on the CVIT benchmark and safety evaluation datasets demonstrate that HPA better maintains high safety and mitigates forgetting than existing baselines.
- Score: 49.76354497916853
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: While continual visual instruction tuning (CVIT) has shown promise in adapting multimodal large language models (MLLMs), existing studies predominantly focus on models without safety alignment. This critical oversight ignores the fact that real-world MLLMs inherently require such mechanisms to mitigate potential risks. In this work, we shift our focus to CVIT for safety-aligned MLLMs and observe that during continual adaptation, the model not only suffers from task forgetting but also exhibits degradation in its safety. Achieving a harmonious balance between safety and task performance remains a crucial challenge. To address this, we propose Harmonious Parameter Adaptation (HPA), a post-training framework composed of focusing-based parameter partition, harmoniously balanced parameter selection, and orthogonal parameter adjustment. Specifically, HPA partitions parameters into two types based on their focus on safety or task performance, and selects the focused ones to preserve from a balanced perspective. In addition, HPA imposes orthogonality constraints on parameter updates to further alleviate catastrophic forgetting. Extensive experiments on the CVIT benchmark and safety evaluation datasets demonstrate that HPA better maintains high safety and mitigates forgetting than existing baselines.
Related papers
- BarrierSteer: LLM Safety via Learning Barrier Steering [83.12893815611052]
BarrierSteer is a novel framework that formalizes safety by embedding learned non-linear safety constraints directly into the model's latent representation space.<n>We show that BarrierSteer substantially reduces adversarial success rates, decreases unsafe generations, and outperforms existing methods.
arXiv Detail & Related papers (2026-02-23T18:19:46Z) - Alignment-Aware Quantization for LLM Safety [30.635936212381726]
Safety and efficiency are important factors when deploying large language models (LLMs)<n>We propose Alignment-Aware Quantization(AAQ), a novel approach that integrates Alignment-Preserving Contrastive( APC) loss into the PTQ pipeline.<n>AAQ is compatible with standard PTQ techniques and enables robust 4-bit (W4A4) quantization across diverse model families.
arXiv Detail & Related papers (2025-11-11T05:24:30Z) - Reimagining Safety Alignment with An Image [49.33281424100804]
Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries.<n>We propose Magic Image, an optimization-driven visual prompt framework that enhances security while reducing over-refusal.
arXiv Detail & Related papers (2025-11-01T11:27:07Z) - 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) - Rethinking Safety in LLM Fine-tuning: An Optimization Perspective [56.31306558218838]
We show that poor optimization choices, rather than inherent trade-offs, often cause safety problems, measured as harmful responses to adversarial prompts.<n>We propose a simple exponential moving average (EMA) momentum technique in parameter space that preserves safety performance.<n>Our experiments on the Llama families across multiple datasets demonstrate that safety problems can largely be avoided without specialized interventions.
arXiv Detail & Related papers (2025-08-17T23:46:36Z) - LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning [61.594212398272184]
Low-Rank Extrapolation (LoX) improves robustness against benign and malicious fine-tuning attacks.<n>LoX leads to 11% to 54% absolute reductions in attack success rates.
arXiv Detail & Related papers (2025-06-18T16:30:02Z) - LookAhead Tuning: Safer Language Models via Partial Answer Previews [62.529794567687354]
Fine-tuning enables large language models to adapt to specific domains, but often compromises their previously established safety alignment.<n>We introduce LookAhead Tuning, a lightweight and effective data-driven approach that preserves safety during fine-tuning.
arXiv Detail & Related papers (2025-03-24T18:11:42Z) - 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)
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.